MOSS-TTS
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
Runs with mockssource: GitHubhomepagePythonApache-2.0commit 934d6826b084
Python, Apache-2.0 licensed. The project labels itself: audio, audio tokenizer, llm, multilingual, multimodal, speech synthesis, streaming and text to audio.
MOSS-TTS runs, with stand-ins for the services it depends on. An Argusic agent installed it in 25 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
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 models (1.7B to 8B params) exceed available RAM.
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.
- pyproject.toml [tool.setuptools] py-modules = [] prevented package discovery - CLI script and package imports failed8 minutes
- mossttsrealtime subpackage not discoverable through editable finder5 minutes
- torch==2.9.1+cu128 not installable on CPU-only machine3 minutes
- moss_tts_local_v1.5 directory name with dot prevents Python package import3 minutes
- moss_tts_delay/__init__.py and moss_tts_realtime/__init__.py missing2 minutes
- moss_soundeffect_v2 requires ftfy, audiotools, diffusers - not all installable2 minutes
- Install time
- 25 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 7 hit, 7 fixed with no human help
- How the result was proved
- FastAPI server started and responded 200 on GET /health with JSON body containing target_sr=24000 and model config; OpenAPI schema returned with 5 endpoints (/health, /tts/session/start, /tts/session/push, /tts/session/{session_id}/audio, /tts/session/close). CLI moss-tts-llama-cpp --help exited 0 with full usage. All core Python modules (moss_tts_delay, moss_tts_local, moss_tts_realtime, llama_cpp subpackage, mossttsrealtime) imported successfully. Text messages of all types (direct TTS, voice cloning, duration control) constructed successfully.
- Model tokens used
- 568,236
- Exact commit tested
- 934d6826b084
- 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.
print(\"INSTALL_SUCCEEDED=true\") print(\"LAUNCH_SUCCEEDED=true\") PYEOF" in /work/repo succeeded in 10292ms: [warmup] Loading backend ... [warmup] Failed: CUDA is required for MossTTSRealtime streaming inference. INSTALL_SUCCEEDED=true LAUNCH_SUCCEEDED=true Now I have all the data I need. Let me compile the final report. tokens used 568,236 Now I have all the data I need. Let me compile the final report.
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
- Recovered from all 7 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
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.
- Took 25 minutes to install, slower than the median of the 6 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 7 audio projects Argusic has installed and timed, MOSS-TTS was the 6th fastest to reach a running state, and 5 of 7 reached one at all.
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 | 1/3 | Runs with mocks | 92.00 | 0.20 |
Topics (from GitHub)
audioaudio-tokenizerllmmultilingualmultimodalspeech-synthesisstreamingtext-to-audiotext-to-speechttsvoice-cloning
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/moss-tts)Questions
- Does MOSS-TTS run?
- MOSS-TTS runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 25 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test MOSS-TTS?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 934d6826b084. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test MOSS-TTS?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does MOSS-TTS take to install?
- 25 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 MOSS-TTS need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing MOSS-TTS?
- 7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does MOSS-TTS compare with the alternatives?
- Of the 7 audio projects Argusic has installed and timed, MOSS-TTS was the 6th fastest to reach a running state, and 5 of 7 reached one at all.
- Where is the evidence for MOSS-TTS?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.