MOSS-TTS-Nano

A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation

Runssource: GitHubhomepagePythonApache-2.0commit 8b7bcc9341b3

Python, Apache-2.0 licensed. The project labels itself: audio tokenizer, chinese, cpu inference, english, multi modality, multilingual, onnx and realtime.

MOSS-TTS-Nano runs. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

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

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 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.08 (measured)
recorded runs
1
last tested
stars
4,430
forks
558
open issues
25
watchers
25
size
58 MB
created
last push

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.

Install time
2 minutes
Cold machine to finish
16 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
infer.py produced valid .wav (ffmpeg -v error -i -f null - exit 0); app.py served /health HTTP 200; POST /api/generate with demo_id=demo-1 returned HTTP 200 with valid 48kHz 2ch 16-bit WAV audio (192000 frames, 4s)
Model tokens used
74,763
Exact commit tested
8b7bcc9341b3
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

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

  wav: channels=2, width=2, rate=48000, frames=192000
DONE
The full stack works end to end. Here's the summary:
- **CLI inference** (`infer.py`): downloaded model from HuggingFace, ran voice-clone TTS on CPU, pr…
- **Web app** (`app.py`): FastAPI server started, served `/health` (200), warmup completed, `POST /…
- No errors were encountered at any stage — no missing packages, no import errors, no API failures.
tokens used
74,763
The full stack works end to end. Here's the summary:
- **CLI inference** (`infer.py`): downloaded model from HuggingFace, ran voice-clone TTS on CPU, pr…
- **Web app** (`app.py`): FastAPI server started, served `/health` (200), warmup completed, `POST /…
- No errors were encountered at any stage — no missing packages, no import errors, no API failures.

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

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 2 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed Apache-2.0, as reported by its host.

What did not, or is not known

  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 2 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.08

Topics (from GitHub)

audio-tokenizerchinesecpu-inferenceenglishmulti-modalitymultilingualonnxrealtimespeech-synthesisstreaming-audiotext-to-speechttsvoice-clonevoice-cloning

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/MOSS-TTS-Nano.svg)](https://argusic.com/subject/moss-tts-nano)

Questions

Does MOSS-TTS-Nano run?
Yes. MOSS-TTS-Nano runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test MOSS-TTS-Nano?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8b7bcc9341b3. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test MOSS-TTS-Nano?
The run that produced this verdict cost $0.08: 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-Nano take to install?
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 MOSS-TTS-Nano need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing MOSS-TTS-Nano?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for MOSS-TTS-Nano?
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.

Discussion