lobe-tts
🎤 Lobe TTS - A high-quality & reliable TTS/STT library for Server and Browser
Runs with mockssource: GitHubhomepageTypeScriptMITcommit d61d820d04ca
TypeScript, MIT licensed. The project labels itself: auzre, bun, edge, lobehub, microsoft speech api, nodejs, opeanai and react.
lobe-tts runs, with stand-ins for the services it depends on. An Argusic agent installed it in 9.2 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
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 requires Node 20+ and is unavailable on the current v18 runtime.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- tsdown build fails because Node v18 lacks node:util styleText export (requires Node 20+)3 minutes
- npm install without --legacy-peer-deps fails with 'Cannot read properties of null (reading edgesOut)'1 minute
- vitest jsdom environment breaks on Node 18 because jsdom v27 is ESM-only1 minute
- Install time
- 9 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npx vitest run passed with 20/20 tests; integration test with local mock HTTP server validated OpenAITTS.create() returns 200 with MP3 audio; esbuild build succeeds; tsc --noEmit passes
- Model tokens used
- 151,293
- Exact commit tested
- d61d820d04ca
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec /bin/sh -lc 'echo "Start time: $(date -d '"'2026-11-22T04:16:45' +%s)\" && echo \"Current time: "'$… succeeded in 0ms: Start time: 1795321005 Current time: 1795321556 exec /bin/sh -lc 'echo "minutes: $(echo "scale=1; ($(date +%s) - 1795321005) / 60" | bc)"' in /work/repo succeeded in 0ms: /bin/sh: 1: bc: not found minutes: tokens used 151,293
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 9.2 minutes.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.03 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.15 |
Topics (from GitHub)
auzrebunedgelobehubmicrosoft-speech-apinodejsopeanaireactspeech-recognitionspeech-to-textstttext-to-speechtts
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/lobe-tts)Questions
- Does lobe-tts run?
- lobe-tts runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 9 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test lobe-tts?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d61d820d04ca. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test lobe-tts?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does lobe-tts take to install?
- 9.2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does lobe-tts need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing lobe-tts?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for lobe-tts?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.