Open source speech to text and text to speech, tested
Speech to text and text to speech tools you can run yourself. The list is ordered by whether each project came up when Argusic installed it fresh, with the recording of that attempt one click away.
Tested between and . Each row shows its own test date; a project can change after that day.
123 of 131 tested projects run. 6 more waiting for a test.
In short: 85 of the 131 tested projects started as-is on a fresh machine: GPT-SoVITS, whisperX, lemo-opuscar, leon, sherpa-onnx, openwhispr, RealtimeSTT, and mlx-audio, and 77 more. 38 more started once a stand-in replaced a service they expect, such as a database: Amphion, ODS, B, elevenlabs-python, vllm-mlx, VibeVoice-ComfyUI, OuteTTS, and hyprwhspr, and 30 more. 8 could not be verified: ai-video-editor, openai-chat-api-workflow, dia, yogurt, dsnote, orbit, NaturalVoiceSAPIAdapter, and watch-skill; the log shows where each one stopped.
Measured by Argusic on a fresh machine every time. Every number links to its evidence.
| # | project | verdict | Argusic Score | language | stars | tested on |
|---|---|---|---|---|---|---|
| 1 | GPT-SoVITS | Runs | 100 / 100 | Python | 64,195 | |
1 min voice data can also be used to train a good TTS model! (few shot voice cloning) What the test found: GPT-SoVITS API server starts and responds to TTS inference requests: HTTP 200 with a valid synthesized WAV audio file returned for English text-to-speech using a default reference audio on CPU. 23 minutes. | ||||||
| 2 | whisperX | Runs | 100 / 100 | Python | 25,593 | |
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization) What the test found: WhisperX 3.8.7rc1 is installed in a Python 3.12 venv at /tmp/whisperx-venv with CPU-only PyTorch. The test suite passes (12/12 tests) and the CLI prints help and version correctly. All imports resolve without errors. 3 minutes. | ||||||
| 3 | lemo-opuscar | Runs | 100 / 100 | JavaScript | 19,824 | |
A toolbox of film styles made in code for Claude Code: 99 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by... What the test found: With Node 20.20.2, the core, voice, and music installs exit 0, and the real pipeline produced a 6.000-second 1920x1080 24 fps film with 144 H.264 frames and stereo AAC audio that fully decoded with exit 0. 7 minutes. | ||||||
| 4 | leon | Runs | 100 / 100 | TypeScript | 17,704 | |
🧠 Leon is your open-source personal assistant. What the test found: Leon server installs, builds, serves HTTP on port 5366, and passes all 371 unit tests with Node.js v24 in CI mode (no local AI or voice models). 10 minutes. | ||||||
| 5 | sherpa-onnx | Runs | 100 / 100 | C++ | 16,099 | |
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet... What the test found: The sherpa-onnx 1.13.8 C++ source built successfully, all 29 CTest tests passed, the published Python package installed, and both Python and native CLI paths performed real Whisper ASR and generated decodable Piper TTS audio. 7 minutes. | ||||||
| 6 | openwhispr | Runs | 100 / 100 | JavaScript | 12,024 | |
Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform. What the test found: npm install succeeds, all 944 tests pass with Node 24 and the custom loader bootstraps, test script runs all test suites without failures. 71 minutes. | ||||||
| 7 | RealtimeSTT | Runs | 100 / 100 | Python | 10,263 | |
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription. What the test found: In a fresh venv with RealtimeSTT[server,faster-whisper] installed, all 591 unit tests pass, the Whisper golden test transcribes the fixture correctly, and the packaged production server answered 200 on /health, /v1/ready and /v1/capabilities and returned the correct transcript on POST /transcribe-pcm16. 9 minutes. | ||||||
| 8 | mlx-audio | Runs | 100 / 100 | Python | 8,323 | |
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple... What the test found: The package installs, all 5 CLI entry points parse their arguments, the API server starts and serves HTTP, and 109 unit tests pass on CPU-only x86_64 Linux. 10 minutes. | ||||||
| 9 | FunClip | Runs | 100 / 100 | Python | 6,622 | |
FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI. What the test found: FunClip v2.2.1 is fully installed in a Python 3.12 venv with all dependencies, all 90 tests pass, the CLI recognition+clipping pipeline processes a real video with Paraformer-Large ASR and produces valid clipped MP4 output, and the Gradio web interface launches and serves HTTP 200 on localhost. 49 minutes. | ||||||
| 10 | abogen | Runs | 100 / 100 | Python | 6,262 | |
Generate audiobooks from EPUBs, PDFs and text with synchronized captions. What the test found: All 1592 tests pass, the Flask web UI serves HTTP on port 8808, and the PyQt6 desktop GUI launches on the virtual display. 13 minutes. | ||||||
| 11 | YouDub-webui | Runs | 100 / 100 | TypeScript | 5,880 | |
Open-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. 开源 AI... What the test found: The app is installed and running: backend answered 200 on /api/health, frontend answered 200 on :3000, all 421 backend and 14 frontend tests pass, and a local-video task ran end to end producing a final mp4 that ffprobe showed as h264+aac and ffmpeg fully decoded. 19 minutes. | ||||||
| 12 | MOSS-TTS-Nano | Runs | 100 / 100 | Python | 4,710 | |
A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation What the test found: MOSS-TTS-Nano ONNX CPU inference works end-to-end: CLI generate produces valid speech WAV files, PyTorch voice cloning produces valid WAV files, and the FastAPI web server starts with a functional /health endpoint. 34 minutes. | ||||||
| 13 | fastrtc | Runs | 100 / 100 | JavaScript | 4,641 | |
The python library for real-time communication What the test found: fastrtc 0.0.34 installed in a Python 3.12 venv; all 29 tests pass including WebRTC offer/answer exchanges, audio format utilities, OpenAPI tag mounting, concurrency limits, and TTS with kokoro-onnx. 32 minutes. | ||||||
| 14 | WhisperLive | Runs | 100 / 100 | Python | 4,364 | |
A nearly-live implementation of OpenAI's Whisper. What the test found: All 318 testspass (14 kipped for optional prometheus_client), the server can be imported and instantiated, the VAD ONNX model is downloaded and functional, and the whisper_live pip package is installed in editable mode in thecontainer's Python 3.12 virtual environment. 16 minutes. | ||||||
| 15 | TTS-WebUI | Runs | 100 / 100 | Go | 3,318 | |
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS... What the test found: TTS-WebUI installs in a Python 3.12 venv via uv, 76/76 tests pass, the CLI troubleshoot command succeeds, and the Gradio server starts on port 7770 accepting connections (returning 502 as expected since gradio proxy tree has no upstream). 7 minutes. | ||||||
| 16 | GPA | Runs | 100 / 100 | Python | 3,054 | |
[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model! What the test found: GPA v1.5 native PyTorch ASR and TTS inference runs successfully on CPU: ASR transcribes Chinese speech accurately, TTS produces 3.96s of voice-cloned speech from a reference audio, and ASR-on-TTS-output roundtrip correctly recognizes the synthesized English text. 12 minutes. | ||||||
| 17 | gTTS | Runs | 100 / 100 | Python | 2,638 | |
Python library and CLI tool to interface with Google Translate's text-to-speech API What the test found: gTTS 2.5.4 is installed, all 124 tests pass, the CLI generates valid MP3 audio from Google's TTS API. 2 minutes. | ||||||
| 18 | pyttsx3 | Runs | 100 / 100 | Python | 2,536 | |
Offline Text To Speech synthesis for python What the test found: pyttsx3 version 2.99 installed in a venv, espeak-ng library and data extracted from Ubuntu Noble .deb packages, the eSpeak TTS driver initializes successfully, all 11 runnable tests pass (5 Apple-specific tests skipped), and save_to_file produces valid 22050 Hz mono 16-bit WAV audio. 5 minutes. | ||||||
| 19 | read-aloud | Runs | 100 / 100 | JavaScript | 1,796 | |
An awesome browser extension that reads aloud webpage content with one click What the test found: All 159 Node.js tests pass, 0 fail, 0 skip. The project builds (npm run package recognizes valid browsers). 7 minutes. | ||||||
| 20 | video-podcast-maker | Runs | 100 / 100 | Python | 1,729 | |
Topic → 4K narrated video for coding agents. v5.3.0: local TTS (edge free + azure, no external engine), manifest-based Asset Engine, Remotion composition... What the test found: Python test suite (255/255 passed), edge TTS synthesis with audio+SRT+timing output, Remotion bundling and still rendering all work end-to-end. 4 minutes. | ||||||
| 21 | amical | Runs | 100 / 100 | TypeScript | 1,650 | |
Free, open source voice typing for macOS and Windows. Local speech-to-text with Whisper and Parakeet, also offline. What the test found: Installation completed: Node 24.10.0, pnpm 10.34.5, all 1566 packages installed, whisper native addon compiled (.node binary at packages/whisper-wrapper/native/linux-x64/whisper.node), electron 44.3.0 available, workspace builds pass, and the test suite runs (149/150 test files pass, 1505/1508 tests pass, 3... 23 minutes. | ||||||
| 22 | soprano | Runs | 100 / 100 | Python | 1,638 | |
Soprano: Instant, Ultra-Realistic Text-to-Speech What the test found: Soprano TTS v0.2.0 is installed and runs on CPU via the transformers backend. The Python API, CLI, and OpenAI-compatible HTTP server all produce valid 32kHz mono WAV audio output. 5 minutes. | ||||||
| 23 | transcribe-anything | Runs | 100 / 100 | Python | 1,489 | |
Multi-backend whisper app. Blazing fast. Mac-arm optimized. Easy install. Input a local file or url and this service will transcribe it using Whisper AI... What the test found: transcribe-anything 4.1.2 installs and local CPU whisper transcription works end-to-end on video.mp4, generating correct out.txt/out.srt/out.vtt; the server daemon boots on port 18765 and responds 200 on /healthz and /docs; 262 of 278 tests pass, 13 skip (GPU/MLX backends), 3 fail due to YouTube bot-detection blocking... 7 minutes. | ||||||
| 24 | SoniTranslate | Runs | 100 / 100 | Python | 1,431 | |
Synchronized Translation for Videos. Video dubbing What the test found: SoniTranslate installs and launches as a Gradio web app on 127.0.0.1:7860 in CPU mode, serving the full video-dubbing UI at HTTP 200. 52 minutes. | ||||||
| 25 | explainroo | Runs | 100 / 100 | JavaScript | 1,399 | |
Explainer videos and product demos made by your AI agent. Free and open source: a local voice (Kokoro), word timing (Whisper) and a canvas renderer turn a... What the test found: explainroo installs, all 38 tests pass, doctor checks green on node/ffmpeg/chrome/voice/speech models, and a 3-scene 19-second test video was written, rendered, verified with 100% speech clarity and no ffmpeg errors. 7 minutes. | ||||||
| 26 | dia2 | Runs | 100 / 100 | Python | 1,189 | |
TTS model capable of streaming conversational audio in realtime. What the test found: uv sync installs all deps; uv run -m dia2.cli generates valid WAV from a script; programmatic API generates audio and returns waveform tensors; Mimi codec decodes correctly; all observed on CPU (no CUDA). 30 minutes. | ||||||
| 27 | agent-plugin | Runs | 100 / 100 | JavaScript | 1,080 | |
AI video editor for agents. ChatCut plugin and MCP server for Codex, ChatGPT, Claude Code, Cursor, Grok, Gemini CLI, WorkBuddy, Doubao Work and Qwen Work: edit... What the test found: All 110 tests pass across 9 test files including plugin metadata validation, symlink integrity, serve-local-media HTTP server (CORS, range, origin, TTL), store package building, and skill content checks. 2 minutes. | ||||||
| 28 | whisper-flow | Runs | 100 / 100 | Python | 1,021 | |
Whisper-Flow is a framework designed to enable real-time transcription of audio content using OpenAI’s Whisper model. Rather than processing entire files after... What the test found: All 29 unit tests pass (97% coverage). The FastAPI server starts, loads the tiny.en Whisper model from disk, serves health/readiness probes, and correctly transcribes real PCM audio via HTTP POST. The PyAudio-dependent hardware capture module is isolated behind lazy imports; microphone/playback features are... 6 minutes. | ||||||
| 29 | VoiceStreamAI | Runs | 100 / 100 | Python | 962 | |
Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS What the test found: VoiceStreamAI server starts and listens on a WebSocket port; all 4 test suites pass with silero VAD and faster-whisper small model on CPU. 42 minutes. | ||||||
| 30 | jiwer | Runs | 100 / 100 | Python | 946 | |
Evaluate your speech-to-text system with similarity measures such as word error rate (WER) What the test found: All 82 tests pass and the jiwer CLI and Python API both work correctly, computing word error rate and related ASR evaluation metrics using RapidFuzz C++ backend. 1 minute. | ||||||
| 31 | vonage-php-sdk-core | Runs | 100 / 100 | PHP | 930 | |
Vonage REST API client for PHP. API support for SMS, Voice, Text-to-Speech, Numbers, Verify (2FA) and more. What the test found: The vonage-php-sdk-core project boots on PHP 8.5.8 with Composer 2.11.2, all 70 dependencies resolve and install, and the full test suite (1096 tests, 5270 assertions) passes with 0 errors and 0 failures. 5 minutes. | ||||||
| 32 | tiny-voca | Runs | 100 / 100 | Python | 850 | |
A 4.5M-parameter two-voice English text-to-speech model, trained from scratch What the test found: All 78 tests pass, the TinyVoca model instantiates correctly with 4,537,291 parameters, the dizione frontend imports and switches, and the inference text-splitting pipeline works. 4 minutes. | ||||||
| 33 | CrispASR | Runs | 100 / 100 | C++ | 826 | |
C++ ggml runtime hub for multilingual ASR and TTS models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment, and more What the test found: CrispASR version 0.8.37 builds from source and passes 1932/1933 hermetic unit tests with the CPU backend on x86_64 Linux, all test binaries produce correct output. 21 minutes. | ||||||
| 34 | claudemy | Runs | 100 / 100 | Python | 714 | |
Claudemy: an open-source alternative to Udemy and Coursera. Give Claude a topic, it researches the web and builds a course of 2-minute audio lessons with cited... What the test found: All 39 regression tests pass. beautifulsoup4 is installed in a venv, ffmpeg is available, all four CLI scripts (scrape, check_lessons, render_audio, package_class) emit correct usage docs, the lesson checker correctly validates scripts and citations, and the package class script combines cards into a deliverable. 2 minutes. | ||||||
| 35 | Playwright-reCAPTCHA | Runs | 100 / 100 | Python | 592 | |
A Python library for solving reCAPTCHA v2 and v3 with Playwright What the test found: All 16 tests execute without errors against live reCAPTCHA demo pages and antcpt.com; v2 solvers correctly raise RecaptchaRateLimitError against Google's rate limits, v3 solvers solve antcpt.com successfully, and recaptcha_not_found tests raise proper exceptions when no captcha is present. 7 minutes. | ||||||
| 36 | ai-avatar-system | Runs | 100 / 100 | Python | 587 | |
🎭 AI Avatar / digital human platform, upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude ·... What the test found: Backend FastAPI server runs on port 8000 with SQLite storage, 191 pytest tests pass, frontend Next.js builds and serves on port 3000, full REST API flow (register/login/me/avatar upload/session create/guest) works end to end in local-dev mode without Docker, Redis, or third-party API keys. 10 minutes. | ||||||
| 37 | speech.cpp | Runs | 100 / 100 | C++ | 518 | |
Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech... What the test found: The speech.cpp 0.10.1 build from source produces a working speech executable and libspeech.so.4 C API shared library on Linux x86_64 CPU. The binary enumerates devices, lists all models in the catalog with their tasks/languages/sizes, downloads models from Hugging Face on demand (verified with silero-vad), runs Silero... 7 minutes. | ||||||
| 38 | Audar-ASR-V1 | Runs | 100 / 100 | Python | 503 | |
Arabic-first generative speech recognition, Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference. What the test found: Audar-ASR-V1-Flash model loads and transcribes on CPU. All three reference API functions (transcribe, transcribe_long, stream_transcribe) work correctly. 27 minutes. | ||||||
| 39 | ai-promo-video-maker | Runs | 100 / 100 | Python | 495 | |
一句话让 AI 帮你做产品宣传片!把产品名或网址告诉 Cursor、Claude Code、Codex 等 AI 编程工具,它会自己调研产品、画出多种风格样图让你挑选、截取 4K 真实页面、按音乐节拍卡点剪辑、生成 AI 旁白并逐句转写校验、自动审图,最后交付一支 4K... What the test found: Template project installs, fonts subset correctly, stills render, 1080p preview video renders cleanly, web player builds; lint passes; all doctor checks pass except optional ElevenLabs key. 10 minutes. | ||||||
| 40 | Lampline | Runs | 100 / 100 | Python | 495 | |
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys... What the test found: Both packages (vpd-vk 0.3.0, vpengine 0.3.0) installed in .venv-engine; 453 tests pass; engine starts and answers health and chat session endpoints. 23 minutes. | ||||||
| 41 | dramaxis | Runs | 100 / 100 | TypeScript | 466 | |
🎬 Dramaxis (剧枢), 电影级多智能体影视叙事与智能解说平台 (Tauri 2 + Rust + React 19)。6 大智能体协同导演、5 轨毫秒级对齐时间轴、四道质量闸门硬核质检、本地优先沙箱架构与剪映草稿深度互通。 What the test found: All 280 frontend tests pass, frontend production build succeeds (299 modules), 10 of 11 Rust workspace crates compile and all their tests pass (core=13, intake=17, export=18), VitePress docs build succeeds. Tauri desktop shell (root Cargo.toml + update crate) blocked by missing libwebkit2gtk-4.1-dev system packages... 11 minutes. | ||||||
| 42 | VoiceFlow | Runs | 100 / 100 | Python | 438 | |
Local voice dictation and meeting recorder for Windows + Linux. Hold a hotkey to dictate, or record long-form meetings with system audio. Whisper... What the test found: pnpm+uv deps installed, TypeScript+Python code compiles/typechecks, frontend Vite build succeeds, 331/331 backend tests pass, and the Qt+Pyloid desktop app launches on the virtual display and loads the Whisper speech model. 22 minutes. | ||||||
| 43 | project-raven | Runs | 100 / 100 | TypeScript | 435 | |
Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures system audio + mic, cancels echo via WebRTC AEC3... What the test found: Raven 2.5.0 Electron app builds from source, runs tests (1088 passed), and launches on Linux with Vite dev server and Electron main process. 3 minutes. | ||||||
| 44 | parakeet-rs | Runs | 100 / 100 | Rust | 421 | |
very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust What the test found: parakeet-rs compiles, all 24 tests pass, and the full ONNX inference pipeline runs successfully with a verified model. 4 minutes. | ||||||
| 45 | vonage-node-sdk | Runs | 100 / 100 | TypeScript | 399 | |
Vonage API client for Node.js. API support for SMS, Voice, Text-to-Speech, Numbers, Verify (2FA) and more. What the test found: The @vonage/server-sdk monorepo installs cleanly under Node 22.23.4, all 618 tests pass, all 28 packages build to CJS/ESM/DTS, lint passes, and a real end-to-end call against a local mock returned a parsed account balance of 10.28 EUR and an SMS response with message-count 1 and status 0. 5 minutes. | ||||||
| 46 | onnx-asr | Runs | 100 / 100 | Python | 392 | |
A lightweight Python package for Automatic Speech Recognition using ONNX models What the test found: All 249 core tests pass, package imports correctly, CLI displays help with all supported model names, and whisper-tiny model executes real ASR inference via Hugging Face. 12 minutes. | ||||||
| 47 | whisper-obsidian-plugin | Runs | 100 / 100 | TypeScript | 382 | |
Speech-to-text in Obsidian using Whisper What the test found: All 69 tests pass (5 test files), TypeScript type-checking passes, esbuild bundles main.js successfully with no errors. 1 minute. | ||||||
| 48 | audiotext | Runs | 100 / 100 | Python | 357 | |
A desktop app to transcribe audio and video from files, URLs, YouTube videos, or your mic, then edit, translate, summarize, subtitle, and chat with your... What the test found: All 554 tests pass, the desktop GUI opens a mapped window on Xvfb, and the CLI transcribes audio files with WhisperX on CPU. 8 minutes. | ||||||
| 49 | xcodec | Runs | 100 / 100 | Python | 318 | |
AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model What the test found: X-Codec model builds, imports, runs encode/decode on real audio across all bandwidths, and produces valid WAV output. 8 minutes. | ||||||
| 50 | whisper.cpp | Runs | 98 / 100 | C++ | 55,429 | |
Port of OpenAI's Whisper model in C/C++ What the test found: whisper.cpp builds from source and transcribes the JFK speech sample correctly with the base.en model on CPU, returning 7 passing tests and a working HTTP server. 5 minutes. | ||||||
| 51 | AI-Powered-Video-Tutorial-Generator | Runs | 98 / 100 | Python | 322 | |
Create and edit AI video tutorials with illustrated lessons, expressive presenters, distinct voices, and a native timeline. Windows desktop app with local... What the test found: All 6 workspace packages build successfully. JS unit tests pass 156/156 (packages/contracts/scenes/themes). Renderer tests pass 100/117 (17 pre-existing version-mismatch failures). Python pipeline tests pass 942/956 (2 pre-existing failures: Linux path normalization vs Windows test, and stale manifest byte count). The... 22 minutes. | ||||||
| 52 | Douyin_TikTok_Download_API | Runs | 97.3 / 100 | Python | 21,518 | |
🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video... What the test found: All 2960 tests pass (2450 unit + 510 integration), the CLI outputs version 5.0.1 and lists 10 commands, the API server starts and serves healthz/readyz/swagger/console root with 200, the web console SPA is built, and both the PostgreSQL+TimescaleDB and Redis backends and the Go downloader sidecar run. 48 minutes. | ||||||
| 53 | whisper-ctranslate2 | Runs | 96.7 / 100 | Python | 1,374 | |
Whisper command line client compatible with original OpenAI client based on CTranslate2. What the test found: whisper-ctranslate2 installed in venv, 17 unit tests pass, CLI transcribes audio files in Catalan on CPU (tiny model) producing txt/srt/vtt/tsv/json output correctly. 1 minute. | ||||||
| 54 | speech_recognition | Runs | 96 / 100 | Python | 9,007 | |
Speech recognition module for Python, supporting several engines and APIs, online and offline. What the test found: SpeechRecognition 3.17.0 installed in a venv; 41 of 56 tests pass with 15 expected skips; Google Speech API recognition returns transcriptions from local audio files; CLI sprc binary prints help. 4 minutes. | ||||||
| 55 | annyang | Runs | 96 / 100 | TypeScript | 6,819 | |
💬 Speech recognition for your site What the test found: All 165 tests pass, build produces ESM/CJS/IIFE bundles in dist/, and the library is usable via npm import or script tag. 11 minutes. | ||||||
| 56 | qwen-audio-agent | Runs | 96 / 100 | JavaScript | 3,265 | |
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents What the test found: The qwen-audio-agent v1.11.0 project installs, builds, launches a Gateway serving HTTP 200 on port 3101, and passes all 1789 automated tests with zero failures. 9 minutes. | ||||||
| 57 | vexa | Runs | 96 / 100 | Python | 3,003 | |
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents... What the test found: 11 Python service test suites and the JS terminal client test suite run successfully in a container with Node 22.13 and Python 3.12.3; the compose/Docker deployment path cannot execute without Docker engine being available. 17 minutes. | ||||||
| 58 | Portable-Local-Studio | Runs | 96 / 100 | JavaScript | 2,087 | |
Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text What the test found: Setup scripts downloaded and extracted all backends (stable-diffusion.cpp CPU+Vulkan, llama.cpp CPU+Vulkan, whisper.cpp CPU, Kokoro TTS), installed frontend dependencies, built React app to app/dist/, the Node.js server starts on port 1420 and serves HTTP 200, and all 13 regression tests pass. 3 minutes. | ||||||
| 59 | LiveStream-Agent-Studio | Runs | 96 / 100 | Python | 2,053 | |
面向抖音直播电商的 Windows 本地 AI Agent Studio,贯通主播发现、直播洞察、直播复盘与短视频内容编导的统一智能工作流。 What the test found: Frontend builds and serves HTTP 200 on port 4173, all 61 tests pass across the frontend and 3 Python agent packages, and the local gateway starts successfully. 3 minutes. | ||||||
| 60 | Genie-TTS | Runs | 96 / 100 | Python | 1,852 | |
GPT-SoVITS ONNX Inference Engine & Model Converter What the test found: GENIE TTS package installs and builds in a Python 3.12 venv; all 4 language G2P modules produce correct phone IDs; FastAPI server serves all endpoints (/stop, /clear_reference_audio_cache, /load_character, /set_reference_audio, /tts, /unload_character) returning HTTP 200; full TTS inference with predefined character... 9 minutes. | ||||||
| 61 | Irodori-TTS | Runs | 96 / 100 | Python | 1,661 | |
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control What the test found: Irodori-TTS installs and all core modules import cleanly on CPU. The TextToLatentRFDiT model constructs and runs forward passes. The Gradio web UI builds and serves HTTP 200. Inference requires downloading a HuggingFace checkpoint. 8 minutes. | ||||||
| 62 | MiniMax-MCP | Runs | 96 / 100 | Python | 1,612 | |
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs. What the test found: The minimax-mcp package is installed in a venv with all 9 unit tests passing: it validates env vars, initializes the MCP server, lists expected tools over both in-process and stdio transports, exercises mocked API calls, and all utility functions (file path building, fuzzy matching, error handling) work correctly. 1 minute. | ||||||
| 63 | Vocello | Runs | 96 / 100 | Swift | 388 | |
Vocello: a private voice studio for Apple Silicon. Write a script, pick or describe a voice, and generate speech locally on your Mac and iPhone. Native Swift... What the test found: On this Linux container the repository's deterministic contract gate passes cleanly, the Python suite passes 1526 tests with 2 unfixable lsof-dependent tests failing, the website's 19 unit tests and production build pass under portable Node 22, and a vite preview server served the prerendered site and both... 12 minutes. | ||||||
| 64 | splicr | Runs | 93.3 / 100 | TypeScript | 466 | |
🎬 Dramaxis (剧枢), 电影级多智能体影视叙事与智能解说平台 (Tauri 2 + Rust + React 19)。6 大智能体协同导演、5 轨毫秒级对齐时间轴、四道质量闸门硬核质检、本地优先沙箱架构与剪映草稿深度互通。 What the test found: Frontend installs, type-checks, builds, and its full Vitest and Playwright suites pass (157 unit tests, 8 e2e tests), and all 12 non-GUI Rust crates build and pass 79 unit plus 2 doc tests; the Tauri desktop shell still cannot be compiled because its system GTK/WebKit dev libraries are absent from this container. 28 minutes. | ||||||
| 65 | TheWhisper | Runs | 93.1 / 100 | Python | 906 | |
Optimized Whisper models for streaming and on-device use What the test found: thestage-speechkit package installs from source with core dependencies; nvidia ASRPipeline transcribes audio with HuggingFace transformers on CPU; streaming library provides StreamingPipeline, ArrayStream, RemoteAPIBackend; FastAPI example server starts and handles create/process/clear/end session endpoints. 12 minutes. | ||||||
| 66 | RealtimeTTS | Runs | 92.7 / 100 | Python | 4,059 | |
Converts text to speech in realtime What the test found: realtimetts 0.8.10 installed and built wheel+sdist; 369 of 380 tests pass covering BaseEngine, alignment, language router, sentence splitting, streaming, stream player, release guard (except ssh-keygen), and Qwen studio; Qwen server starts and fails only on CUDA GPU requirement; pyttsx3 SystemEngine requires espeak. 13 minutes. | ||||||
| 67 | minutes | Runs | 92.5 / 100 | Rust | 1,614 | |
Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed... What the test found: minutes CLI v0.27.0 builds and installs from source in this container. It records, transcribes with Whisper tiny, generates AI summaries via the codex agent CLI, produces searchable markdown meeting files, and passes 1826 of 1870 unit tests (38 worker/ffmpeg tests fail only because the test harness cannot find a... 34 minutes. | ||||||
| 68 | dograh | Runs | 92 / 100 | Python | 6,242 | |
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow... What the test found: Backend Python venv installed with all core deps, PostgreSQL 16 running on port 5432, Redis 7.4.1 running on port 6379, Node.js v22 deployed, pipecat submodule installed editable, FastAPI app imports with speechmatics as the only blocking provider, 493/514 collectable tests pass against real services. 57 minutes. | ||||||
| 69 | claude-code-video-toolkit | Runs | 91 / 100 | Python | 2,710 | |
Make videos with Claude Code: script, AI voiceover, music, video clips and render, on open-source models that cost cents What the test found: Hello-world, sprint-review template, render-baseline test, and concept-explainer-short template all render valid MP4 videos; migration script fixed and installs all 27 skills/commands; verify_setup.py confirms all prerequisites met. 16 minutes. | ||||||
| 70 | whisper-asr-webservice | Runs | 90 / 100 | Python | 3,370 | |
OpenAI Whisper ASR Webservice API What the test found: The Whisper ASR Box webservice is installed and running: the uvicorn server serves Swagger UI at /docs, returns JSON language detection at /detect-language, and returns transcription text at /asr all with HTTP 200. 14 minutes. | ||||||
| 71 | transcribe.cpp | Runs | 90 / 100 | C++ | 2,197 | |
ggml speech-to-text inference for 16+ model families What the test found: transcribe.cpp builds from source with cmake and GCC 13, produces a working transcribe-cli binary that understands all CLI options and reads 16 kHz mono WAV files, and passes all 39 unit/smoke tests on CPU without a model file. 4 minutes. | ||||||
| 72 | read-aloud | Runs | 90 / 100 | JavaScript | 1,796 | |
An awesome browser extension that reads aloud webpage content with one click What the test found: Read Aloud extension package builds cleanly (474KB ZIP), all 49 JS files pass node syntax check, the extension loads into Chromium 127 via Playwright without errors, manifest declares all TTS permissions and a service worker, and 14 distinct TTS engine implementations are wired in tts-engines.js. 5 minutes. | ||||||
| 73 | ComfyUI-OmniVoice-TTS | Runs | 90 / 100 | Python | 567 | |
OmniVoice TTS nodes for ComfyUI - Zero-shot multilingual text-to-speech with voice cloning, voice design, and multi-speaker dialogue What the test found: 5 OmniVoice TTS ComfyUI nodes (Longform TTS, Voice Clone, Voice Design, Multi-Speaker, Whisper Loader) installed and registered; OmniVoice-bf16 model loads from HuggingFace cache, generates valid 24kHz audio waveform from text on CPU in ~9 seconds for 2-second utterance. 5 minutes. | ||||||
| 74 | heard | Runs | 89.3 / 100 | Python | 1,104 | |
Open-source (Apache 2.0) voice tool for Claude Code and Codex on macOS that reads your coding agent's progress aloud. The voice runs locally with Kokoro, no... What the test found: Heard Python package v1.1.48 installed and importable; CLI functional; 871/872 relevant tests pass on Linux (the 1 failure is macOS-specific afplay binary missing); ruff lint clean. 3 minutes. | ||||||
| 75 | WhisperJAV | Runs | 82 / 100 | Python | 2,498 | |
ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV What the test found: Project installed from source at /work/repo with 79 packages in a Python 3.12 venv. All 4 verification commands pass: import, --version (1.9.3), --help (full CLI), --dump-params (safe config probe). 617/617 clean tests pass; 43 failures and 11 errors are pre-existing (version drift, restructured config, missing... 11 minutes. | ||||||
| 76 | MOSS-TTSD | Runs | 70 / 100 | Python | 1,425 | |
A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and zero-shot voice cloning What the test found: MOSS-TTSD v1.0 model loads from HuggingFace, processor encodes conversations, forward pass returns logits, and generate() produces audio codes and text tokens on CPU with bfloat16 precision. 25 minutes. | ||||||
| 77 | Handy | Runs | 60 / 100 | Rust | 39,679 | |
A free, open source, and extensible speech-to-text application that works completely offline. What the test found: The Handy app builds from source (debug binary + frontend), passes its full Rust unit test suite (271/271) and Playwright frontend tests (2/2), and launches and stays up on the Xvfb virtual display, enumerating its CPU compute device and 69-model catalog via CLI. 67 minutes. | ||||||
| 78 | hex | Runs | 60 / 100 | Rust | 8,117 | |
Local voice dictation for mac, windows and linux What the test found: Full Rust project compiles on Ubuntu 24.04 x86_64 with no root, all 397 unit tests pass (0 failures), binary runs and responds to --help and --version commands. 28 minutes. | ||||||
| 79 | yovoice | Runs | 60 / 100 | TypeScript | 2,287 | |
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores, 100% offline, zero API fees. What the test found: 安装、前端构建、Go 核心测试(3 包通过)与 Playwright 浏览器测试(74/74 通过)全部成功,浏览器预览应用服务返回 HTTP 200,独立 CLI(engine v0.7.4)与 audiocpp CPU 引擎(0.7.4)均能启动运行;仅原生桌面 App 因仓库限 macOS/Windows 未在此 Linux 容器构建。. 10 minutes. | ||||||
| 80 | voxtype | Runs | 60 / 100 | Rust | 1,813 | |
Voice-to-text with push-to-talk for Wayland compositors What the test found: Voxtype v1.1.0 builds and passes its full test suite (1159 passed, 0 failed) on Ubuntu 24.04 amd64 with Rust 1.99.0, after manually providing alsa and clang/LLVM development libraries extracted from apt packages without root privileges. The CLI binary responds correctly to --version and --help. 27 minutes. | ||||||
| 81 | ComfyUI_Custom_Nodes_AlekPet | Runs | 60 / 100 | JavaScript | 1,536 | |
Custom nodes that extend the capabilities of Comfyui What the test found: The repository installs as a ComfyUI custom_nodes extension: pip dependencies install cleanly, ComfyUI starts on CPU, the server answers HTTP 200, and all 8 AlekPet custom node groups load successfully with zero startup errors. 34 minutes. | ||||||
| 82 | chaplin | Runs | 60 / 100 | Python | 781 | |
A real-time silent speech recognition tool. What the test found: AVSR model loads on CPU and produces transcriptions from video features; MediaPipe face detector initializes; all Python imports resolve; webcam capture fails in headless environment (no /dev/video0) but app otherwise works. 23 minutes. | ||||||
| 83 | flutter_edge_ai | Runs | 60 / 100 | Dart | 671 | |
On-device AI for Flutter, Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux. What the test found: All 14 Dart pub workspace packages with test directories pass their test suites on Linux x64 with Flutter 3.47.0 and Dart 3.13.0, with 0 errors and all 567 analyzer findings at info level only. 11 minutes. | ||||||
| 84 | VRCT | Runs | 60 / 100 | Python | 463 | |
VRCT(VRChat Chatbox Translator & Transcription) What the test found: Python backend starts and completes full initialization (Whisper model, CTranslate2, OSC), Vite frontend builds and serves, all 936 pytest tests pass, OCR engine is ready with downloaded models, Rust toolchain installed; Tauri native build blocked by missing webkit2gtk-4.1 system libraries (not installable without... 25 minutes. | ||||||
| 85 | LocalText2Voice | Runs | 58 / 100 | Python | 438 | |
Free open-source AI desktop app for audiobooks, podcasts, documentaries, films and animated videos with local models, cloud APIs and editable storyboards. What the test found: Dependencies installed, 819 non-multimedia tests pass (0 failures), the engine host HTTP server answers 200 on /health, and 4 code/test bugs were fixed; the Qt GUI cannot launch because no PipeWire audio daemon runs in this container. 31 minutes. | ||||||
| 86 | Amphion | Runs with mocks | 92 / 100 | Python | 10,347 | |
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and... What the test found: Core dependencies installed, evaluation metrics compute correctly on audio pairs, model classes import cleanly. pyworld-dependent f0 metrics unavailable without python3-dev headers. Cython monotonic_align extension uncompiled for same reason. 25 minutes. | ||||||
| 87 | ODS | Runs with mocks | 92 / 100 | Python | 7,900 | |
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server. What the test found: Project builds correctly, all 418 bats tests, 14/14 smoke tests (after ai_err fix), ~300 shell/Python contract tests, and the vite frontend build pass. The Docker runtime install cannot complete in this environment, but the dry-run installer, CLI (-v2.6.0), all standalone test suites, and the frontend are functional. 15 minutes. | ||||||
| 88 | B | Runs with mocks | 92 / 100 | Python | 5,176 | |
An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active window tracking... What the test found: B boots successfully on Linux inside Xvfb virtual display, initializing all 17 modules (EventBus, KinematicsEngine, WindowManager, FaceRenderer, ChatBubble, InputBox, StateMachine, CognitiveEngine with mock Groq, SemanticVisionSensor, VisionSensor, WindowTracker with polling fallback, AutonomyEngine, VoiceEngine with... 22 minutes. | ||||||
| 89 | elevenlabs-python | Runs with mocks | 92 / 100 | Python | 3,194 | |
The official Python SDK for the ElevenLabs API. What the test found: elevenlabs 2.69.0 installs and imports in Python 3.12; 203/219 tests pass (16 fail due to missing API key); all hand-maintained wrapper modules load correctly; the pyaudio optional dependency cannot build (no python3-dev). 3 minutes. | ||||||
| 90 | vllm-mlx | Runs with mocks | 92 / 100 | Python | 1,658 | |
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling... What the test found: vllm-mlx 0.5.0 installed in a venv with all dependencies; 1585 Linux-compatible unit tests pass, 19 skip on non-Apple-Silicon, 0 failed; all 4 CLI entry points print help successfully. 19 minutes. | ||||||
| 91 | VibeVoice-ComfyUI | Runs with mocks | 92 / 100 | Python | 1,582 | |
A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly... What the test found: All 41 tests pass: 6 node modules import correctly with ComfyUI stubs, text chunking/pause parsing/silence generation work, model scanning detects valid model folders including HuggingFace cache format, file loading and memory management nodes function, all third-party dependencies install cleanly, and the embedded... 8 minutes. | ||||||
| 92 | OuteTTS | Runs with mocks | 92 / 100 | Python | 1,440 | |
Interface for OuteTTS models. What the test found: OuteTTS v0.4.4 Python package installed in venv with all 17+ submodules importing; JS package installed with 12/12 vitest tests passing; configuration layer (ModelConfig, GenerationConfig, SamplerConfig, auto_config) verified functional for all backends and models; actual TTS generation requires downloading models... 6 minutes. | ||||||
| 93 | hyprwhspr | Runs with mocks | 92 / 100 | Python | 1,288 | |
Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation What the test found: The Python test suite passes fully (1146/1146, 7 expected skips for missing optional system tools xkbcli/gsettings). The CLI launches and responds to all commands (--help, --version, status, config show). The project is installable from clone via pip into a venv using requirements-test.txt, and all code is importable... 3 minutes. | ||||||
| 94 | VoxtMini | Runs with mocks | 92 / 100 | Go | 920 | |
Voice input for macOS on local models: transcribe, translate and rewrite in any app. The successor of Voxt. What the test found: All 356 Go tests pass on Linux with Go 1.27.4, CJK fonts installed, lint clean, and mygo vet clean; the Swift helper, Omni runtime, and macOS binary are not built in this environment. 9 minutes. | ||||||
| 95 | lobe-tts | Runs with mocks | 92 / 100 | TypeScript | 810 | |
🎤 Lobe TTS - A high-quality & reliable TTS/STT library for Server and Browser What the test found: Dependencies install with --legacy-peer-deps; TypeScript type-check passes; esbuild produces es/ output directory; 20 unit tests pass covering EdgeSpeechTTS, OpenAITTS, MicrosoftSpeechTTS, VoiceList, and cleanContent; mock-server integration confirms OpenAITTS HTTP fetch/create pattern works correctly; tsdown build... 10 minutes. | ||||||
| 96 | expo-speech-recognition | Runs with mocks | 92 / 100 | TypeScript | 700 | |
Speech Recognition for React Native Expo projects What the test found: The library builds and type-checks, its example web app serves and renders with no page or console errors, and its web speech module start/stop/event wiring works against a mock SpeechRecognition in Chrome. 53 minutes. | ||||||
| 97 | openlrc | Runs with mocks | 92 / 100 | Python | 684 | |
Transcribe and translate voice into LRC file using Whisper and LLMs (GPT, Claude, et,al). 使用whisper和LLM(GPT,Claude等)来转录、翻译你的音频为字幕文件。 What the test found: openlrc 1.7.0a2 is installed and built in a Python 3.12 venv; all 186 mock-based unit tests pass; the httpx/httpx2 compatibility bug in ClaudeBot and GPTBot constructors is fixed. 27 minutes. | ||||||
| 98 | meetingly-ai | Runs with mocks | 92 / 100 | TypeScript | 670 | |
Open-source AI interview assistant and meeting copilot: live answers during Zoom, Google Meet and Teams calls, on-device transcription, hidden from screen... What the test found: The app installs and builds on the bundled toolchain, 123 unit tests and 44 relay tests pass, the Electron app launches (windows visible on Xvfb), and a chat request travels from the built app through the local relay to the OpenAI-compatible mock upstream and back with HTTP 200. 10 minutes. | ||||||
| 99 | examples | Runs with mocks | 92 / 100 | TypeScript | 637 | |
What the test found: All 17 examples install and run: every Next.js example builds (pnpm run build exit 0) and its / and API routes answered 200 against schema-correct local mocks returning real decodable MP3 audio, transcripts, and tokens; the CLI TS/Python quickstarts produced output.mp3 (ffmpeg-decode clean) or printed the transcript... 64 minutes. | ||||||
| 100 | aspeak | Runs with mocks | 92 / 100 | Rust | 495 | |
A simple text-to-speech client for Azure TTS API. What the test found: aspeak 6.1.0 builds and runs from source with PKG_CONFIG_PATH and LIBRARY_PATH workarounds; CLI text and SSML synthesis, stdout output, and offline subcommands (list-formats, list-qualities, --help, --version) all work; real Azure endpoint tests skipped due to missing credentials. 10 minutes. | ||||||
| 101 | deepgram-python-sdk | Runs with mocks | 92 / 100 | Python | 478 | |
Official Python SDK for Deepgram. What the test found: deepgram-sdk 7.10.0 is installed in a Poetry virtualenv and its full test suite passes (1052 passed, 4 skipped) against a local WireMock-compatible mock, with sync and async client calls returning parsed typed responses and ruff plus mypy clean. 7 minutes. | ||||||
| 102 | mouse-mcp | Runs with mocks | 92 / 100 | TypeScript | 473 | |
Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmware. 面向 AI 智能体的硬件鼠标... What the test found: TypeScript build succeeds, all 257 unit tests pass (0 failures, 21 skipped), all 39 inject tests pass, MCP server starts and responds to protocol handshake with 22 tools and correct version 0.1.0; Windows native SDK DLL and hardware are not available on this Linux x64 platform. 4 minutes. | ||||||
| 103 | MsEdgeTTS | Runs with mocks | 92 / 100 | TypeScript | 347 | |
A simple Azure Speech Service module that uses the Microsoft Edge Read Aloud API. https://migushthe2nd.github.io/MsEdgeTTS/ What the test found: pnpm install and TypeScript build succeed, all 10 Jest tests pass using a local WebSocket mock of the Microsoft Edge Read Aloud API. 26 minutes. | ||||||
| 104 | Whisper-TikTok | Runs with mocks | 92 / 100 | Python | 344 | |
From AI tools to TikTok video creation using FFMPEG, Microsoft Edge read aloud and OpenAI Whisper model What the test found: Package installs (uv sync --frozen), CLI help works, list-voices queries real Edge TTS API returning 9 Male + 8 Female English voices, create pipeline runs end-to-end with yt-dlp YouTube download, Whisper transcription, FFmpeg video composition delivering a valid 2.3MB MP4, and pytest passes 1/1. 7 minutes. | ||||||
| 105 | sayna | Runs with mocks | 92 / 100 | Rust | 318 | |
Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks | ||||||
| 106 | voicy | Runs with mocks | 90 / 100 | JavaScript | 915 | |
Voicy (@voicybot): a Telegram bot that turns voice messages into text in groups and private chats What the test found: TypeScript compiles cleanly, Express webhook server starts and enforces authentication, and 31 unit/proof tests pass against an in-memory MongoDB, covering transcription caching, job lifecycle, abuse limits, donation formatting, webhook handling, and activity stream emitters. 4 minutes. | ||||||
| 107 | mimi | Runs with mocks | 89.5 / 100 | Rust | 952 | |
把电脑或麦克风声音转成实时翻译字幕。Live translated subtitles from computer or microphone audio. What the test found: The mimi Tauri app builds, its full Rust test suite passes (421/421), the frontend builds and all TypeScript tests pass (120/120), and the release binary launches on the virtual X display, creating all three windows and registering keyboard shortcuts before staying alive until killed. 36 minutes. | ||||||
| 108 | ai-skills | Runs with mocks | 86.3 / 100 | Python | 458 | |
24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI, databases, messaging, research, TTS, DevOps, and Google Workspace What the test found: All Python deps install and the full pytest suite passes (11 passed, 1 skipped); Outline, Telegram, Google TTS, ElevenLabs, Imagen, and NotebookLM E2E smoke are verified working against local mocks with production defaults preserved, while real-database skills and credential-gated third-party skills remain unverified... 40 minutes. | ||||||
| 109 | MOSS-TTS | Runs with mocks | 86 / 100 | Python | 4,360 | |
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS What the test found: MOSS-TTS Python package installs and builds; FastAPI server starts and serves /health endpoint on port 8768; CLI entry point prints usage; all core Python modules import; the project is ready for model weight download and GPU inference but cannot run inference in this container because no CUDA GPU is available and the... 31 minutes. | ||||||
| 110 | mlx-audio | Runs with mocks | 82.7 / 100 | Python | 8,323 | |
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple... What the test found: mlx-audio v0.5.6 installed in a Python venv with mlx[cpu] backend, 354 of 376 tests pass (22 skipped due to missing torch/diffusers for parity), FastAPI server starts and responds 200 on /v1/models, all five CLI tools print help. 8 minutes. | ||||||
| 111 | ComfyUI-VibeVoice | Runs with mocks | 81 / 100 | Python | 615 | |
ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio What the test found: ComfyUI-VibeVoice v2.11.0 core modules and nodes install successfully; 1365 of 1634 tests pass under mocked ComfyUI stubs; remaining 230 failures require a real ComfyUI installation with model weights and GPU. 31 minutes. | ||||||
| 112 | Patter | Runs with mocks | 71 / 100 | Python | 1,087 | |
Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines, Python and... What the test found: Python SDK installs and runs 3037 passing tests. TypeScript SDK installs, compiles with zero errors, builds, and all test files pass. Python CLI responds with usage text. Two code bugs (SSRF IPv4-mapped blocking, mtime tiebreaker) and one tooling issue (vitest/vite version mismatch) were diagnosed and fixed. 41 minutes. | ||||||
| 113 | Mimi | Runs with mocks | 66.4 / 100 | Rust | 952 | |
把电脑或麦克风声音转成实时翻译字幕。Live translated subtitles from computer or microphone audio. What the test found: In this container, mimi builds cleanly (all check.sh gates green) and the dev binary launches and stays up on the Xvfb display with settings, overlay, control and tray windows mapped, its UI-test synthetic session toggling between listening and idle via the Ctrl+Shift+Space global shortcut; real provider calls and... 36 minutes. | ||||||
| 114 | TalkingHead | Runs with mocks | 56 / 100 | JavaScript | 1,696 | |
Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars. What the test found: TalkingHead 3D avatar library installed with npm, local brunette.glb avatar loads successfully in headless Chrome via WebGL, and the full test suite of 32 streaming API tests passes with 0 failures. 14 minutes. | ||||||
| 115 | quillman | Runs with mocks | 56 / 100 | Python | 1,214 | |
A voice chat app What the test found: The QuiLLMan frontend and websocket adapter run locally via uvicorn on port 8000 with a mocked Modal layer serving both the React frontend (200 on /) and a FastAPI websocket endpoint (200 on /status, echo responses on /ws). 11 minutes. | ||||||
| 116 | botium-speech-processing | Runs with mocks | 56 / 100 | JavaScript | 943 | |
Botium Speech Processing What the test found: The Botium Speech Processing frontend server runs on port 56000 serving status, STT, TTS, languages, voices, and Swagger endpoints, with mock backends for MaryTTS and Kaldi substituting for the Docker-dependent default services. 6 minutes. | ||||||
| 117 | sonus | Runs with mocks | 56 / 100 | JavaScript | 639 | |
:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection What the test found: With the recorded workarounds, the project's dependencies install, the snowboy native addon and grpc load, ESLint passes, the snowboy detector fires the hotword on real audio, and sonus's hotword-to-recognition flow works against a mock speech recognizer. 17 minutes. | ||||||
| 118 | openreader | Runs with mocks | 56 / 100 | TypeScript | 594 | |
An open-source read-along document reader server with high-quality TTS options, synchronized highlighting, and audiobook export for EPUB, PDF, DOCX, TXT, and... What the test found: Node.js v22.12.0 with pnpm 10.33.4 installed, all 810 unit tests pass (0 failed), TypeScript type checking clean for both main app and compute-worker, production build compiles successfully, linting and boundary checks pass, and the development server starts and serves all pages (root, signin, signup) with HTTP 200. 8 minutes. | ||||||
| 119 | ComfyUI-VoxCPM | Runs with mocks | 56 / 100 | Python | 523 | |
ComfyUI node for highly expressive speech and realistic zero-shot voice cloning What the test found: ComfyUI-VoxCPM v2.4.0 loads in ComfyUI 0.42.0 on CPU; all 6 custom nodes registered under audio/tts categories; test suite runs 61/62 passing; ComfyUI server starts and responds on --cpu flag; frontend JS extension served; model scanning, settings, validation, and configuration types all verified standalone. 9 minutes. | ||||||
| 120 | izwi | Runs with mocks | 52.7 / 100 | Rust | 480 | |
Voice AI that runs on your own machine: speech-to-text, text-to-speech, voice cloning, diarization, and voice chat behind an OpenAI-compatible API. Desktop... What the test found: Izwi CLI 0.1.0-beta-18 and HTTP API server compile and run on linux-x86_64 with CPU backend; all 3169+ unit tests pass across 7 workspace crates; server serves OpenAI-compatible /v1/ endpoints on port 8080 with proper health, metrics, model listing, OpenAPI docs, and web UI; desktop Tauri shell cannot build due to... 30 minutes. | ||||||
| 121 | meetily | Runs with mocks | 47.3 / 100 | Rust | 32,962 | |
Privacy-first AI meeting note taker for Windows, macOS and Linux. Free, open source (MIT). On-device Whisper/Parakeet transcription and speaker diarization, no... What the test found: Meetily Tauri app builds from source, all Rust (188) and frontend (8) tests pass, and the desktop app launches successfully on Xvfb, initializing all subsystems including Tauri GUI, notification system, database, tray icon, and model managers. 61 minutes. | ||||||
| 122 | parlor | Runs with mocks | 46 / 100 | Python | 2,117 | |
On-device, real-time multimodal AI with features similar to GPT-Live What the test found: Project installs, builds, and the server starts with Gemma 4 E2B loaded and serving HTTP+WebSocket; the end-to-end AI pipeline (turn detection, llama.cpp inference, transcript parsing, TTS) all initialize and run correctly when tested manually, but the full test suite cannot complete because CPU-only inference exceeds... 77 minutes. | ||||||
| 123 | elevenlabs-js | Runs with mocks | 46 / 100 | TypeScript | 456 | |
The official JavaScript (Node) library for the ElevenLabs API. What the test found: The repository installs with npm, builds with tsc, and its full Jest suite (1094 tests, 179 suites) plus a 22-check SDK probe pass under Node 20 against a local schema-correct mock of the ElevenLabs API, with generated mp3 audio verified by ffmpeg decode and WebSocket realtime/speech-engine paths verified live. 19 minutes. | ||||||
| 124 | ai-video-editor | Could not verify | 80 / 100 | JavaScript | 1,002 | |
Open-source, local-first video editor where creators and AI agents edit the same real timeline. What the test found: npm install, TypeScript typecheck, and Vite build all pass; the dev server starts and serves the application at localhost:5173; the headless timeline CLI command engine parses commands and returns structured JSON errors. 9 minutes. | ||||||
| 125 | openai-chat-api-workflow | Could not verify | 80 / 100 | Ruby | 318 | |
🎩 An Alfred 5 Workflow for using OpenAI Chat API to interact with GPT models 🤖💬 It also allows image generation/editing/understanding 🖼️, speech-to-text... What the test found: Ruby 3.4.7 installed via Conda; all 21 source files pass syntax check; 11 of 12 test files pass (the lone failure is a macOS-only afplay assertion); the WEBrick HTTP server boots and serves pages correctly; the HTML page builder produces complete output. 6 minutes. | ||||||
| 126 | dia | Could not verify | 50 / 100 | Python | 19,417 | |
A TTS model capable of generating ultra-realistic dialogue in one pass. What the test found: Package nari-tts installs and all modules import, config loads from HF, CLI help parses, and audio utility functions work correctly, but the 1.6B-parameter model cannot load on this container's 755 MB of RAM (needs at least 3.2 GB). 10 minutes. | ||||||
| 127 | yogurt | Could not verify | 20 / 100 | TypeScript | 2,948 | |
Private AI meeting notes that stay on your computer. No meeting bot. Free and open source for Mac, Windows and Linux. An alternative to Granola, Otter and... What the test found: could not be verified; the log shows where it stopped. 19 minutes. | ||||||
| 128 | dsnote | Could not verify | 20 / 100 | C++ | 1,721 | |
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation. What the test found: CMake configured successfully in build_final2 with Qt6 6.4.2, Catch2, fmt, ffmpeg; full build fails at dsnote_lib because 18+ external C/C++ API symbols from webrtc_vad, rnnoise, espeak-ng, piper, april-asr, sam, rdrview, cld2, google_pinyinim, xdo, qhotkey, libarchive, taglib, ssplitcpp, maddy, html2md, cpp-pinyin... 48 minutes. | ||||||
| 129 | orbit | Could not verify | 10 / 100 | Python | 366 | |
Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents. What the test found: could not be verified; the log shows where it stopped. 28 minutes. | ||||||
| 130 | NaturalVoiceSAPIAdapter | Could not verify | 9.3 / 100 | C++ | 1,026 | |
Make Azure natural TTS voices accessible to any SAPI 5-compatible application. What the test found: x64 release binaries (TtsApplication.exe and NaturalVoiceSAPIAdapter.dll) extracted from GitHub release v0.2.9 and run under a manually-extracted wine-9.0 environment with zlib1.dll provided from MSYS2 mingw64, the GUI app launches and stays running, and the COM DLL registers successfully via regsvr32. 20 minutes. | ||||||
| 131 | watch-skill | Could not verify | 0 / 100 | Python | 605 | |
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work... What the test found: watch-skill 1.4.3 installed with all extras; 2215 offline tests pass; ruff clean; CLI reports all dependencies operational; lint checks pass. 88 minutes. | ||||||
| - | opentypeless | Not yet verified | - | Rust | 699 | - |
| - | SpeakoFlow | Not yet verified | - | Rust | 406 | - |
| - | manim-voiceover | Not yet verified | - | Python | 328 | - |
| - | VidBee | Not yet tested | - | TypeScript | 11,201 | - |
| - | podcast-maker | Not yet tested | - | TypeScript | 711 | - |
| - | sdk | Not yet tested | - | TypeScript | 344 | - |
runs installed and started with its real dependencies. runs with mocks started after stand-ins replaced external services such as a database or a third-party API. could not verify neither the standard agent nor the stronger one got it running within the time limit; the log shows where it stopped.
How we tested
On this list as of the latest test: 85 projects ran as-is, 38 with mocks, 8 could not be verified, 6 still waiting. Languages tested: C++, Dart, Go, JavaScript, PHP, Python, Ruby, Rust, Swift, TypeScript. Every attempt used a clean single-use machine, the subject at a pinned version, and a 90-minute limit for standard projects; the complete procedure is on the methodology page.
Frequently asked questions (FAQs)
How is this list ranked?
By measurement, not opinion: projects Argusic installed and launched on a fresh machine come first, then those that ran with mocks in place of external services, then those it could not verify. Ties go to the Argusic Score, then how popular it is on its own source.
Why are some projects unranked?
6 projects are still waiting for a test or for a finished attempt. They are listed without a rank until Argusic has measured them.
Where is the evidence?
Every row links to the project's Argusic page, where each run has a full log and a terminal recording stored with a sha256 fingerprint. The same pages exist for every one of the tested projects, on this list or not.
More lists in this category
- self-hosted AI apps (shares FunClip, Lampline, ODS, amical, meetily, opentypeless, orbit with this list)
- open source video editors (shares AI-Powered-Video-Tutorial-Generator, FunClip, agent-plugin, ai-video-editor, dramaxis, splicr with this list)
- MCP servers (shares Douyin_TikTok_Download_API, MiniMax-MCP, agent-plugin, vexa with this list)
- AI agent frameworks (shares Douyin_TikTok_Download_API, lemo-opuscar with this list)
- open source coding agents (shares heard, qwen-audio-agent with this list)
- LLM gateways (shares orbit with this list)
- ebook readers (shares openreader with this list)
- low-code platforms (shares dograh with this list)
- vector databases (shares orbit with this list)
- web scraping tools (shares Douyin_TikTok_Download_API with this list)
- workflow automation tools (shares ODS with this list)
- API clients
- API gateways
- CI/CD tools
- CMS platforms
- VPN tools
- backup tools
- browser automation tools
- code editors
- Open source databases, installed and queried
- developer CLI tools
- e-commerce platforms
- game engines
- open source games
- home automation tools
- map tools
- message queues
- Open source music servers, installed and played
- observability tools
- Open source office suites, installed and launched
- self-hosted password managers
- project management tools
- screen recorders
- search engines
- self-hosted analytics
- static site generators
- uptime monitors
- video players
- whiteboard tools
- wikis
- self-hosted Notion alternatives
- self-hosted dashboards
- self-hosted git servers