Open-Source-Spracherkennung und Sprachsynthese, getestet

1 min Sprachdaten können auch verwendet werden, um ein gutes TTS-Modell zu trainieren! (Few-Shot-Stimmklonen)

Was der Test ergab: 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 Minuten.

WhisperX: Automatische Spracherkennung mit wortgenauen Zeitstempeln (und Diarisierung)

Was der Test ergab: 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 Minuten.

Leon ist Ihr persönlicher Assistent, der open source ist.

Was der Test ergab: 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 Minuten.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation und VAD mit Kaldi der nächsten Generation und onnxruntime ohne...

Was der Test ergab: 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 Minuten.

Eine Toolbox mit Filmstilen, in Code für Claude Code erstellt: 66 sofort einsatzbereite Stile und Ihre eigenen. Jeder Stil besteht aus einem Style-Prompt plus...

Was der Test ergab: 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 Minuten.

Sprache-zu-Text-Diktier-App mit lokalen (Nvidia Parakeet/Whisper) und Cloud-Modellen (BYOK). Datenschutzorientiert und auf vielen Plattformen verfügbar.

Was der Test ergab: npm install succeeds, all 944 tests pass with Node 24 and the custom loader bootstraps, test script runs all test suites without failures. 71 Minuten.

Eine robuste, effiziente Bibliothek mit geringer Latenz für die Umwandlung von Sprache in Text, mit erweiterter Sprachaktivitätserkennung, Aktivierung per Wake...

Was der Test ergab: 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 Minuten.

Spracherkennungsmodul für Python, das mehrere Engines und APIs unterstützt, online und offline.

Was der Test ergab: 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 Minuten.

Eine Text-zu-Sprache (TTS), Sprache-zu-Text (STT) und Sprache-zu-Sprache (STS) Bibliothek, die auf Apples MLX Framework basiert und effiziente Sprachanalyse...

Was der Test ergab: A fresh editable install exited 0, the API server returned HTTP 200 on / and /v1/models, a real Kokoro request produced a decodable 2.8-second 24 kHz mono WAV, and the combined core and TTS test suites passed 1506 tests with 45 skipped. 39 Minuten.

Spracherkennung für Ihre Website

Was der Test ergab: All 165 tests pass, build produces ESM/CJS/IIFE bundles in dist/, and the library is usable via npm import or script tag. 11 Minuten.

Ein FunASR-basiertes Tool für Videotranskription, Untertitelgenerierung und LLM-gestützte Clip-Erstellung mit lokaler Gradio-Oberfläche.

Was der Test ergab: 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 Minuten.

Audiobooks aus EPUBs, PDFs und Text mit synchronisierten Untertiteln generieren.

Was der Test ergab: All 1592 tests pass, Flask web UI serves HTTP 200 on GET /, and the real Kokoro-82M TTS engine with af_heart voice generates non-silent, ffmpeg-decodable WAV audio from text input. 22 Minuten.

Open-Source-Sprach-KI-Plattform. Selbst gehostete Alternative zu Vapi und Retell. On Prem, BYOK für Speech to Speech oder LLM/STT/TTS, mit einem visuellen...

Was der Test ergab: 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 Minuten.

Open-Source-KI-Videolokalisierung und -Synchronisation für YouTube/Bilibili: Spracherkennung, Untertitelübersetzung, Stimmklonen, Audiomischung und Rendering...

Was der Test ergab: Backend API is fully operational: uvicorn serves the FastAPI app on port 9998, all 421 backend tests pass, and every major endpoint (health, login, tasks, settings, cookies) responds correctly with expected status codes. 20 Minuten.

Lokales Sprachdiktat für mac, windows und linux

Was der Test ergab: 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 Minuten.

Die python-Bibliothek für Echtzeitkommunikation

Was der Test ergab: The fastrtc library installs in a venv, all 29 tests pass, the Kokoro TTS model generates audio, and a demo app starts under uvicorn and serves its OpenAPI schema. 7 Minuten.

Ein 100M-Parameter mehrsprachiges TTS-Modell für Echtzeit-CPU-Inferenz, Stimmenklonen und 48-kHz-Stereo-Generierung

Was der Test ergab: Dependencies installed in venv; PyTorch CPU inference via infer.py produces valid WAV audio; FastAPI web server responds to health checks and generates 48kHz stereo speech via POST /api/generate with demo presets. 16 Minuten.

Eine nahezu Live-Implementierung von OpenAI's Whisper.

Was der Test ergab: WhisperLive is installed in a Python 3.12 venv with all dependencies, 318 of 332 unit tests pass (14 metrics tests skipped as they require a dedicated metrics server port), and the server launches with the REST API health endpoint responding HTTP 200 on port 8000 and the WebSocket server listening on port 9090. 11 Minuten.

Konvertiert Text in Sprache in Echtzeit

Was der Test ergab: 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 Minuten.

OpenAI Whisper ASR Webservice-API

Was der Test ergab: 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 Minuten.

Eine einzige Gradio + React WebUI mit Erweiterungen für ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice...

Was der Test ergab: TTS-WebUI server starts and responds HTTP 200 on both Gradio proxy (7767) and main (7770) interfaces; 102 of 105 tests pass (3 skipped require real API credentials); all core extensions import cleanly; CLI troubleshoot passes. 6 Minuten.

[AutoArk] GPA (General Purpose Audio) kann ASR, TTS und Stimmkonvertierung mit einem winzigen Modell durchführen!

Was der Test ergab: GPA v1.5 native PyTorch ASR, TTS, and training all run on CPU with weights downloaded from HuggingFace. ASR transcribes Chinese and English correctly; TTS produces valid 16 kHz mono audio from text plus a reference clip; training executes a forward/backward step. 10 Minuten.

Open-Source-Meeting-Transkriptions-API für Google Meet, Microsoft Teams & Zoom. Auto-Join-Bots, Echtzeit-WebSocket-Transkripte, MCP-Server für AI-Agenten...

Was der Test ergab: 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 Minuten.

Python-Bibliothek und CLI-Tool zur Anbindung an die text-to-speech API von Google Translate

Was der Test ergab: gTTS 2.5.4 installed, all 108 pytest tests pass, and the CLI generates valid MP3 audio via the Google Translate TTS API. 1 Minute.

Offline Text-To-Speech-Synthese für Python

Was der Test ergab: pyttsx3 v2.99 with eSpeak-NG v1.53.0 backend on Python 3.12.3 (Linux): import, speech synthesis, WAV file saving, property get/set, event loop, and all 9 applicable tests pass. 4 Minuten.

ggml Sprache-zu-Text-Inferenz für 16+ Modellfamilien

Was der Test ergab: 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 Minuten.

Open-Source-Studio für lokale KI-Audio- und Musikproduktion für macOS und Windows. Sie erhalten TTS, Stimmklonen, Lieder mit Texten und mehrspurige Scores via...

Was der Test ergab: 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 Minuten.

GPT-SoVITS ONNX-Inferenz-Engine & Modellkonverter

Was der Test ergab: 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 Minuten.

Eine tolle Browser-Erweiterung, die Webseiteninhalte mit einem Klick vorliest.

Was der Test ergab: All 159 tests pass consistently (0 fail, 0 skipped, 0 todo) across repetitive concurrent execution; the offscreen-manager fixture timeout was relaxed to eliminate a timing-dependent failure. 3 Minuten.

Sprach-zu-Text mit Push-to-Talk für Wayland-Compositoren

Was der Test ergab: 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 Minuten.

Thema → 4K-Video mit Erzählung für Coding Agents. v5.3.0: lokale TTS (edge kostenlos + azure, keine externe Engine), manifest-basierte Asset Engine...

Was der Test ergab: All 255 Python tests pass, TypeScript type-checks pass, and Remotion 4.0.438 renders a 2-frame smoke test to a valid H.264 MP4 verified with ffmpeg decode check; the only source change needed was bumping zod from ^3.23.0 to ^4.3.6 in package.json. 7 Minuten.

Soprano: Sofortige, ultrarealistische Text-to-Speech

Was der Test ergab: Soprano TTS 0.2.0 is installed from source in a venv at /tmp/venv. The CLI produces valid 32 kHz WAV audio on CPU. The FastAPI server serves the /v1/audio/speech endpoint (HTTP 200, valid WAV). The Gradio WebUI module loads successfully. Streaming playback requires the system PortAudio library (not available in this... 15 Minuten.

AI Dictation App - Open Source und Local-first Tippen Sie 3x schneller, keine Tastatur nötig. Angetrieben von Open-Source-Modellen, funktioniert offline...

Was der Test ergab: 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 Minuten.

Benutzerdefinierte Knoten, die die Fähigkeiten von Comfyui erweitern

Was der Test ergab: 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 Minuten.

Ein Flow-Matching-basiertes Text-to-Speech-Modell mit Emoji-gesteuerter Stilsteuerung

Was der Test ergab: 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 Minuten.

Multi-Backend-whisper-App. Rasend schnell. Für Mac-arm optimiert. Einfache Installation. Geben Sie eine lokale Datei oder URL ein, und dieser Dienst...

Was der Test ergab: transcribe-anything 4.1.2 installed in a uv-managed Python 3.11 venv with Python 3.10 available for iso-envs; 265/278 tests pass, CLI help works, all backends ready for first-use env creation. 21 Minuten.

Synchronisierte Übersetzung für Videos. Video-Synchronisation.

Was der Test ergab: SoniTranslate web app built with Gradio 4.19.2 launches via python app_rvc.py --cpu_mode and serves a fully constructed UI at http://127.0.0.1:7860 returning HTTP 200 on / and /config endpoints. 22 Minuten.

Ein mehrsprachiges Modell für Langform-Mehrsprecher-Dialogsynthese mit flexibler Sprechersteuerung und Zero-Shot-Stimmklonierung.

Was der Test ergab: 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 Minuten.

TTS-Modell, das in Echtzeit Konversationsaudio streamen kann.

Was der Test ergab: Dia2-1B model loads and generates valid 24 kHz mono WAV audio on CPU (bfloat16) via both the Python API and CLI, producing non-silent output with correct speaker-tagged transcription and word timestamps. 12 Minuten.

Whisper-Flow ist ein Framework, das die Echtzeit-Transkription von Audioinhalten mithilfe des Whisper-Modells von OpenAI ermöglicht. Anstatt nach dem Upload...

Was der Test ergab: Whisper Flow V1.1.0 server launches on port 8181, serves /health (200) and /ready (200) endpoints showing model loaded and 0 active sessions, all 29 core tests pass with 97% coverage, and all core modules import correctly. 18 Minuten.

Nahezu-Echtzeit-Transkription von Audio mit selbst gehostetem Whisper und WebSocket in Python/JS

Was der Test ergab: A fresh venv installs cleanly; the VoiceStreamAI server launches on 127.0.0.1:8765 with the token-free silero VAD plus the real faster-whisper-tiny model and streams a real transcription back over WebSocket ('Good morning, everyone!'), while 2 of 3 unittest tests pass and the pyannote VAD test remains blocked by the... 15 Minuten.

Evaluieren Sie Ihr Spracherkennungssystem mit Ähnlichkeitsmaßen wie der Wortfehlerrate (WER).

Was der Test ergab: The jiwer package is installed and functional: all 74 tests pass, the CLI prints its help, and the Python API computes WER/MER/WIL/WIP/CER correctly including empty-reference edge cases. 1 Minute.

Vonage REST API Client für PHP. API-Unterstützung für SMS, Voice, Text-to-Speech, Numbers, Verify (2FA) und mehr.

Was der Test ergab: Vonage client-core installs with composer update and its full PHPUnit suite passes 1096/1096 after the Guzzle 8 version-guard fix in src/Client.php, with SMS send verified end-to-end against a local mock HTTP client. 4 Minuten.

Erklärvideos und Produktdemos, erstellt von Ihrem KI-Agenten. Kostenlos und Open Source: eine lokale Stimme (Kokoro), Wort-Timing (Whisper) und ein...

Was der Test ergab: explainroo v0.1.0 is installed with Node.js 20.20.2, Playwright Chromium headless shell, Kokoro TTS, Whisper ASR, and all npm dependencies. The project initializes, voices, checks, stills, sheets, and renders draft MP4s. The how-dns-works example produces a 68s video with 8 scenes. 29 Minuten.

C++-ggml-Runtime-Hub für mehrsprachige ASR- und TTS-Modelle: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universelles Forced Alignment...

Was der Test ergab: CrispASR v0.8.37 builds, runs CLI transcription (Whisper base model), and serves an HTTP API, all tested end-to-end with real audio in this container. 36 Minuten.

Claudemy: eine Open-Source-Alternative zu Udemy und Coursera. Sie geben Claude ein Thema, es recherchiert im Web und erstellt einen Kurs aus 2-minütigen...

Was der Test ergab: 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 Minuten.

Eine Python-Bibliothek zum Lösen von reCAPTCHA v2 und v3 mit Playwright.

Was der Test ergab: 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 Minuten.

KI-Avatar-/Digital-Human-Plattform: Laden Sie ein Foto hoch, klonen Sie eine Stimme und sprechen Sie mit jedem Gesicht in Echtzeit mit Lippen-synchronem Video...

Was der Test ergab: 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 Minuten.

Erstellen Sie AI-Telefon-Agents auf Ihrem eigenen Computer und testen Sie jede Änderung mit einem AI-Anrufer. Open Source, läuft kostenlos ohne API-Schlüssel...

Was der Test ergab: 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 Minuten.

Arabisch-zuerst generative Spracherkennung: Audar-ASR-V1 (Flash + Turbo). #1 auf dem Open Universal Arabic ASR Leaderboard. Modellkarten, Benchmarks und...

Was der Test ergab: Audar-ASR-V1-Flash model loads and transcribes on CPU. All three reference API functions (transcribe, transcribe_long, stream_transcribe) work correctly. 27 Minuten.

Dramaxis (剧枢): eine filmreife Multi-Agenten-Plattform für Film- und Fernseh-Erzählungen und intelligente Erklärungen (Tauri 2 + Rust + React 19). 6 große...

Was der Test ergab: 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 Minuten.

Mit einem Satz zur KI-Produktwerbung: Geben Sie Cursor, Claude Code oder Codex den Produktnamen oder die URL. Das Tool recherchiert, entwirft Stilstichproben...

Was der Test ergab: 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 Minuten.

Lokales Sprachdiktat und Meeting-Recorder für Windows + Linux. Halten Sie einen Hotkey zum Diktieren oder zeichnen Sie lange Besprechungen mit Systemaudio auf...

Was der Test ergab: 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 Minuten.

Open-Source-KI-Meeting-Copilot, Echtzeit-Transkription, Echounterdrückung und KI-Assistenz. Erfasst Systemaudio + Mikrofon, unterdrückt Echo via WebRTC AEC3...

Was der Test ergab: 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 Minuten.

Sehr schnelle Spracherkennung, Diarisierung, Streaming (sogar auf CPU) mit NVIDIA Parakeet in Rust

Was der Test ergab: parakeet-rs compiles, all 24 tests pass, and the full ONNX inference pipeline runs successfully with a verified model. 4 Minuten.

Vonage API client for Node.js. API-Unterstützung für SMS, Voice, Text-to-Speech, Numbers, Verify (2FA) und mehr.

Was der Test ergab: 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 Minuten.

Ein leichtgewichtiges Python-Paket für automatische Spracherkennung mit ONNX-Modellen

Was der Test ergab: 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 Minuten.

Sprache-zu-Text in Obsidian mit Whisper

Was der Test ergab: All 69 tests pass (5 test files), TypeScript type-checking passes, esbuild bundles main.js successfully with no errors. 1 Minute.

Eine Desktop-App, um Audio und Video aus Dateien, URLs, YouTube-Videos oder Ihrem Mikrofon zu transkribieren und dann Ihre Transkripte zu bearbeiten, zu...

Was der Test ergab: All 554 tests pass, the desktop GUI opens a mapped window on Xvfb, and the CLI transcribes audio files with WhisperX on CPU. 8 Minuten.

AAAI 2025: Codec ist wichtig: Untersuchung der semantischen Schwäche des Codecs für Audio-Sprachmodelle

Was der Test ergab: X-Codec model builds, imports, runs encode/decode on real audio across all bandwidths, and produces valid WAV output. 8 Minuten.

Port von OpenAIs Whisper-Modell in C/C++

Was der Test ergab: 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 Minuten.

Erstellen und Bearbeiten von KI-Video-Tutorials mit illustrierten Lektionen, ausdrucksstarken Moderatoren, unterschiedlichen Stimmen und einer nativen...

Was der Test ergab: 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 Minuten.

Selbst gehosteter Scraper für TikTok, Douyin und Bilibili sowie Downloader für Videos ohne Wasserzeichen: asynchrone REST-API, MCP-Server für AI agents, CLI...

Was der Test ergab: 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 Minuten.

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

Was der Test ergab: 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 Minuten.

Vocello: ein privates Sprachstudio für Apple Silicon. Schreiben Sie ein Skript, wählen Sie eine Stimme aus oder beschreiben Sie eine, und erzeugen Sie Sprache...

Was der Test ergab: 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 Minuten.

Whisper Befehlszeilen-Client kompatibel mit dem ursprünglichen OpenAI-Client basierend auf CTranslate2.

Was der Test ergab: Installed in a venv; the CLI answers version 0.5.7, all 17 unit tests pass, and 6 of 7 e2e tests pass including real small/medium-model transcription of the bundled samples matched against reference outputs, with only diarization failing because it needs a real HuggingFace token and pyannote/torch. 22 Minuten.

Dramaxis (剧枢), filmreifes Multi-Agent-Plattform für Film- und Fernseherzählung und intelligente Erklärung (Tauri 2 + Rust + React 19). 6 intelligente Agenten...

Was der Test ergab: 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 Minuten.

ASR/STT-Untertitelgenerator. Verwendet Qwen3-ASR, lokales LLM, Whisper, TEN-VAD. Rauschresistent für JAV.

Was der Test ergab: 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 Minuten.

AI-natives Videoproduktions-Toolkit für Claude Code

Was der Test ergab: 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 Minuten.

Eine großartige Browser-Erweiterung, die Webseiteninhalte mit einem Klick vorliest.

Was der Test ergab: 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 Minuten.

OmniVoice TTS Nodes für ComfyUI: Zero-shot mehrsprachige Text-to-Speech mit Voice Cloning, Voice Design und Multi-Speaker-Dialog

Was der Test ergab: 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 Minuten.

Open-Source- und lokal-zuerst-Alternative zu Granola/Otter, die Claude Code, Codex, Cursor und jeder MCP-Client abfragen können. Besprechungen, Anrufe und...

Was der Test ergab: The minutes CLI v0.27.0 binary builds and runs: 59 commands available, demo generates 5 sample meetings with correct markdown frontmatter and YAML metadata, capabilities endpoint reports 50+ features, whisper-guard passes 14/14 tests, 1827/1864 minutes-core tests pass with 37 container-limited failures, 3/4... 30 Minuten.

Eine kostenlose, Open-Source- und erweiterbare Sprach-zu-Text-Anwendung, die vollständig offline funktioniert.

Was der Test ergab: 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 Minuten.

Ein Tool zur Echtzeit-Erkennung von stiller Sprache.

Was der Test ergab: 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 Minuten.

On-Device-KI für Flutter: Gemma und andere LLMs, multimodal, Function Calling, Embeddings, RAG und Sprache auf Android, iOS, Web, macOS, Windows und Linux.

Was der Test ergab: 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 Minuten.

VRCT(VRChat Chatbox Übersetzer & Transkription)

Was der Test ergab: 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 Minuten.

Kostenlose Open-Source-KI-Desktop-App für Hörbücher, Podcasts, Dokumentarfilme, Filme und animierte Videos mit lokalen Modellen, Cloud-APIs und bearbeitbaren...

Was der Test ergab: 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 Minuten.

Amphion (/æmˈfaɪən/) ist ein Toolkit für Audio-, Musik- und Sprachgenerierung. Sein Zweck ist es, reproduzierbare Forschung zu unterstützen und...

Was der Test ergab: 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 Minuten.

Eine Bibliothek für Text-to-Speech (TTS), Speech-to-Text (STT) und Speech-to-Speech (STS), die auf Apples MLX-Framework basiert und effiziente Sprachanalyse...

Was der Test ergab: 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 Minuten.

ODS V3 Pre-Release: Öffentliche Tests und Verfeinerung vor dem offiziellen V3-Start. Verwandeln Sie Ihren PC, Mac oder Linux-Rechner in einen privaten...

Was der Test ergab: 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 Minuten.

Ein autonomer, kontextbewusster KI-Desktop-Begleiter. Erstellt mit Python, mit Echtzeit-Bildschirmvision, benutzerdefinierter ONNX-Sprachsynthese, aktiver...

Was der Test ergab: All 18 modules initialize correctly: EventBus, KinematicsEngine, WindowManager, FaceRenderer, ChatBubble, InputBox, StateMachine, CognitiveEngine (Groq mode), Vision sensors (semantic + mss), WindowTracker, AutonomyEngine, and VoiceEngine all boot to 'B is alive' with the Qt event loop running at ~62fps. Windows-only... 28 Minuten.

Eine Open-Source-Modellfamilie für Langform-Sprache, Dialogsynthese, Stimmdesign, Soundeffekte und Echtzeit-Streaming-TTS

Was der Test ergab: 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 Minuten.

Das offizielle Python SDK für die ElevenLabs API.

Was der Test ergab: The elevenlabs Python SDK v2.69.0 is installed in a venv and all 219 tests pass using httpx.MockTransport to mock ElevenLabs API endpoints. 15 Minuten.

Lokale multimodale KI in Echtzeit mit Funktionen, die GPT-Live ähneln.

Was der Test ergab: 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 Minuten.

Ein lokales Windows-AI-Agent-Studio für Douyin-Live-Commerce, das Streamer-Discovery, Live-Stream-Insights, Live-Stream-Review und Kurzvideo-Content-Regie zu...

Was der Test ergab: The web UI serves 200 with the LiveAgent Studio title, the local gateway health endpoint verifies both mock DashScope and mock OSS as configured/verified, all 37+16+3 agent unit tests plus the frontend build tests pass, and the full video breakdown pipeline produced and decoded a real timestamped Excel transcript. 27 Minuten.

Portables lokales KI-Studio für Windows, Linux und macOS. GUI ohne Einrichtung für Bildgenerierung, GGUF-LLMs, Text-to-Speech & Speech-to-Text.

Was der Test ergab: Frontend deps installed, React UI builds and is served on localhost:1420, all 13 regression tests pass, server API endpoints respond correctly. 7 Minuten.

Talking Head (3D): Eine JavaScript-Klasse für Echtzeit-Lip-Sync mit Ganzkörper-3D-Avataren.

Was der Test ergab: 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 Minuten.

Hochleistungs-LLM-Inferenzserver für Apple Silicon, kompatibel mit OpenAI und Anthropic. Native MLX, kontinuierliches Batching, multimodale Modelle...

Was der Test ergab: vllm-mlx 0.5.0 installs into a venv on x86 Linux, its CLI help command prints usage for 8 subcommands, and 1559 of its Linux-compatible unit tests pass. 23 Minuten.

Offizieller MiniMax Model Context Protocol (MCP)-Server, der die Interaktion mit leistungsstarken Text-to-Speech-, Bildgenerierungs- und Videogenerierungs-APIs...

Was der Test ergab: Package installed in a venv, all 9 pre-existing tests pass (3 server + 6 utils), and the MCP server binary launches and waits for stdio input. 2 Minuten.

Eine umfassende ComfyUI-Integration für Microsofts VibeVoice Text-zu-Sprache-Modell, die hochwertige Einzel- und Mehrsprecher-Sprachsynthese direkt in Ihren...

Was der Test ergab: 5/5 nodes registered. Torch 2.14.1+cu130, Transformers 4.57.6, Diffusers 0.39.0. Needs real model files + Qwen2.5-1.5B tokenizer for TTS. 22 Minuten.

Schnittstelle für OuteTTS-Modelle.

Was der Test ergab: outetts 0.4.4 installed with all dependencies including llama-cpp-python 0.3.9 (CPU), Python modules import cleanly, default speakers load, JS test suite 12/12 passes. 15 Minuten.

Native Spracherkennung für Linux: schnell, genau, privat und hackbare systemweite Diktierfunktion.

Was der Test ergab: Python venv with all test and runtime dependencies installed; 1146/1146 tests pass; CLI responds correctly for help, config, status, transcribe routing; main service blocked only by missing system libportaudio2 which requires root to install. 17 Minuten.

Eine Sprach-Chat-App

Was der Test ergab: 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 Minuten.

Botium Sprachverarbeitung

Was der Test ergab: 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 Minuten.

Lobe TTS - Eine hochwertige und zuverlässige TTS/STT-Bibliothek für Server und Browser.

Was der Test ergab: Dependencies installed; library builds and type-checks on Node 22.14.0; createEdgeSpeech connects to a WebSocket, sends speech.config and ssml frames, and returns a 200 Response containing the mocked audio payload. 17 Minuten.

Spracherkennung für React Native Expo-Projekte

Was der Test ergab: 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 Minuten.

Transkribieren und übersetzen Sie Sprachaufnahmen in LRC-Dateien mit Whisper und LLMs (GPT, Claude, usw.). Verwenden Sie Whisper und LLMs (GPT, Claude usw.)...

Was der Test ergab: 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 Minuten.

Was der Test ergab: 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 Minuten.

Ein einfacher Text-to-Speech-Client für die Azure TTS API.

Was der Test ergab: 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 Minuten.

Offizielles Python-SDK für Deepgram.

Was der Test ergab: 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 Minuten.

Open-Source-KI-Interview-Assistent und Meeting-Copilot: Live-Antworten während Zoom-, Google-Meet- und Teams-Anrufen, Transkription auf dem Gerät, vor...

Was der Test ergab: 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 Minuten.

Ein einfaches Azure Speech Service-Modul, das die Microsoft Edge Read Aloud API verwendet.

Was der Test ergab: pnpm install and TypeScript build succeed, all 10 Jest tests pass using a local WebSocket mock of the Microsoft Edge Read Aloud API. 26 Minuten.

Von AI-Tools zur TikTok-Videoerstellung mit FFMPEG, Microsoft Edge read aloud und OpenAI Whisper model

Was der Test ergab: 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 Minuten.

Sayna ist eine einheitliche Voice Layer für AI Agents mit nahtloser Integration in bestehende agentenbasierte Frameworks.

Voicy (@voicybot): ein Telegram-Bot, der Sprachnachrichten in Gruppen und privaten Chats in Text umwandelt.

Was der Test ergab: The repo installs and builds (yarn install + tsc), and 32 proof scripts including the worker end-to-end vNext QAs pass against a locally-started mongod; live-Telegram checks were not run because they need a real bot token, and the local-whisper proof was made platform-independent. 6 Minuten.

Computer- oder Mikrofon-Audio in Live-Übersetzungsuntertitel umwandeln.

Was der Test ergab: Full Rust library unit-test suite (421 tests) passes, frontend vitest suite (120 tests) passes, TypeScript typecheck and production Vite build succeed, ESLint clean, with all system GTK/WebKit GLib dependencies resolved from apt-downloaded .deb packages extracted to a local prefix. 21 Minuten.

Optimierte Whisper-Modelle für Streaming und den Einsatz auf dem Gerät

Was der Test ergab: In this container the Python package installs and imports, the streaming pipeline and examples/server.py run against a local mock ASR endpoint returning word timestamps, and the Electron client launches on the virtual display and completes a session-create/audio-chunk/process transcription round trip; real CUDA/CoreML... 34 Minuten.

24 plattformübergreifende Agent-Skills für Claude Code, Cursor, Codex & Gemini CLI: Datenbanken, Messaging, Recherche, TTS, DevOps und Google Workspace

Was der Test ergab: 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 Minuten.

ComfyUI-Custom-Node für die VibeVoice TTS. Ausdrucksstarkes, langformatiges Mehrsprecher-Konversationsaudio.

Was der Test ergab: 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 Minuten.

Open-Source-Sprach-KI-SDK. Die Vapi/Retell-Alternative für Entwickler, die den Stack selbst besitzen möchten. Geben Sie Ihrem AI-Agenten in 4 Zeilen eine...

Was der Test ergab: 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 Minuten.

Wandeln Sie Audio von Ihrem Computer oder Mikrofon in Echtzeit-übersetzte Untertitel um.

Was der Test ergab: 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 Minuten.

:speech_balloon: /so.nus/ STT (Spracherkennung) für Node mit Offline-Hotword-Erkennung

Was der Test ergab: 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 Minuten.

Ein Open-Source-Read-Along-Dokumentenlese-Server mit hochwertigen TTS-Optionen, synchronisierter Hervorhebung und Hörbuch-Export für EPUB, PDF, DOCX, TXT und...

Was der Test ergab: 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 Minuten.

ComfyUI-Knoten für hoch ausdrucksstarke Sprache und realistisches Zero-Shot-Stimmklonen

Was der Test ergab: 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 Minuten.

Sprach-KI-Laufzeit. Lokale Transkription zuerst, Sprecher-Diarisierung, TTS und Stimmklonen mit einer OpenAI-kompatiblen API.

Was der Test ergab: 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 Minuten.

Datenschutzorientierte KI-Notiz-App für Windows und macOS. Kostenlos, Open Source (MIT). Lokale Whisper/Parakeet-Transkription und Sprecher-Diarisierung, kein...

Was der Test ergab: 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 Minuten.

Die offizielle JavaScript-Bibliothek (Node) für die ElevenLabs API.

Was der Test ergab: 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 Minuten.

Open-Source-Videoeditor, der lokal zuerst arbeitet: Ersteller und AI-Agenten bearbeiten dieselbe echte Timeline.

Was der Test ergab: 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 Minuten.

Ein Alfred 5 Workflow zur Nutzung der OpenAI Chat API zur Interaktion mit GPT-Modellen. Er ermöglicht auch Bildgenerierung/-bearbeitung/-verständnis...

Was der Test ergab: 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 Minuten.

Ein TTS-Modell, das in der Lage ist, ultra-realistischen Dialog in einem Durchlauf zu generieren.

Was der Test ergab: 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 Minuten.

Speech Note Linux-App. Notizen machen, Lesen und Übersetzen mit Offline-Speech-to-Text, Text-to-Speech und maschineller Übersetzung.

Was der Test ergab: 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 Minuten.

Selbst gehostetes AI-Gateway für privates RAG, Datenzugriff in natürlicher Sprache und Tool-aufrufende Agenten.

Was der Test ergab: konnte nicht verifiziert werden; das Log zeigt, wo es stehen blieb. 28 Minuten.

Machen Sie natürliche Azure-TTS-Stimmen für jede SAPI-5-kompatible Anwendung zugänglich.

Was der Test ergab: 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 Minuten.

Geben Sie KI-Agenten Augen, Ohren und verifizierbare Ergebnisse. Watch Skill verwandelt Video, Audio und Bildschirmaktivität in durchsuchbare, mit Zeitstempeln...

Was der Test ergab: watch-skill 1.4.3 installed with all extras; 2215 offline tests pass; ruff clean; CLI reports all dependencies operational; lint checks pass. 88 Minuten.