Meta MMS-TTS
by Meta (FAIR)
Family of small VITS text-to-speech checkpoints, one per language, covering over 1,100 languages.
Voiceover (text-to-speech) Open source
1. Price: huggingface.co/facebook/mms-tts-eng
Open weights, free to download; self-hosted.
huggingface.co/facebook/mms-tts-engNo quote yet: price is read from the official pages.
2. Commercial use: github.com/facebookresearch/fairseq/tree/main/examples/mms
“The MMS code and model weights are released under the CC-BY-NC 4.0 license.”
The license does not allow commercial use of the code or weights.
github.com/facebookresearch/fairseq/tree/main/examples/mms3. Credit the author: github.com/facebookresearch/fairseq/tree/main/examples/mms
“The MMS code and model weights are released under the CC-BY-NC 4.0 license.”
Speech: Meta MMS-TTS (facebook/mms-tts), CC BY-NC 4.0, https://creativecommons.org/licenses/by-nc/4.0/
github.com/facebookresearch/fairseq/tree/main/examples/mms4. Agent access: github.com/facebookresearch/fairseq
There is no package or API. Files are downloaded by hand from the official site.
github.com/facebookresearch/fairseqLicense checked Oct 25, 2026 against 1 official page. Tap a verdict to see its source. How we checked Report an error
Meta MMS-TTS: free speech voices for 1,100+ languages
MMS-TTS is a family of free text-to-speech voices from Meta, one small voice file per language, covering over a thousand languages. You or your AI assistant run it on your own computer to turn written text into spoken audio. It is for non-commercial projects only, such as research, teaching or hobby work.
Where you can use it
Speech in languages paid voices skip
Hear text read aloud in a language that big voice services do not offer, for a study, a class or a community project. Each language has its own voice, picked by its three-letter code.
Audio files from a script
Turn a list of sentences into sound files on your own computer, for example short prompts for a language lesson or a museum audio guide that is not sold.
Text in non-Latin scripts
Languages written in other alphabets, such as Korean or Arabic, need one extra free package that turns the text into Latin letters first. The voice then reads it as usual.
Faster or slower reading
Make the voice read faster or slower, for example slower for language learners. One setting changes the speed of the whole clip.
Read-aloud on a hobby site Idea
Add a listen button to a free, non-commercial site, such as a community dictionary or a school project. Make the audio files ahead of time and serve them like any other file.
Try a language before buying a voice Idea
Hear how a new language sounds in your app's flow before you choose a paid voice for the real product. Swap in the paid voice before launch.
As reported by Meta (FAIR): Text-to-speech models for over 1,100 languages; The facebook/mms-tts collection page lists 1107 languages.
Meta MMS-TTS popularity
How to start
Tell your AI assistant
“Use Meta MMS-TTS through transformers (pinned version, 4.33 or newer) to read my sentences aloud in <language code>, with set_seed for repeatable output, and save one WAV per sentence; this project is non-commercial.”
Or install it yourself.
pip install --upgrade transformers accelerate
Show codeStep 1 or Step 2
Load the voice for your language by its code (facebook/mms-tts-<code>) and turn text into a waveform.
model = VitsModel.from_pretrained("facebook/mms-tts-eng")
tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
Save the result as a WAV file at the model's sampling rate.
scipy.io.wavfile.write("techno.wav", rate=model.config.sampling_rate, data=output.float().numpy())
Mistakes to avoid
The weights are under a non-commercial license.
The docs squeeze the batch dimension before saving, so the file holds one channel of audio.
VITS adds randomness to rhythm, so output changes between runs.
pip install -U uroman, then check tokenizer.is_uromanThose voices were trained on romanized text.
pip install --upgrade transformers with no version, as the model card showsThe model needs 4.33+, and an unpinned upgrade can change behaviour between runs of your project.
License
CC-BY-NC-4.0 (code and weights) license. Free only for non-commercial use, under CC BY-NC 4.0. Credit Meta, link the license and say if you changed anything. Paid apps, client work and monetized videos are not allowed.
“The MMS code and model weights are released under the CC-BY-NC 4.0 license.” github.com/facebookresearch/fairseq/tree/main/examples/mms
“The MMS code and model weights are released under the CC-BY-NC 4.0 license.” github.com/facebookresearch/fairseq/tree/main/examples/mms
“The MMS code and model weights are released under the CC-BY-NC 4.0 license.” github.com/facebookresearch/fairseq/tree/main/examples/mms
Sharing the weights is allowed for non-commercial purposes with credit, a license link and a note of changes.
“provide a link to the license, and indicate if changes were made” creativecommons.org/licenses/by-nc/4.0
“The MMS code and model weights are released under the CC-BY-NC 4.0 license.” github.com/facebookresearch/fairseq/tree/main/examples/mms
AllowedWith conditionsNot allowedNot stated or not checked yet
Is Meta MMS-TTS free for commercial use? The full answer Not legal advice. Check the license page before you ship.
For your agent
License rules tell your agent what it may do with Meta MMS-TTS. Paste them into your prompt or AGENTS.md.
- Meta MMS-TTS (Voiceover (text-to-speech)). Family of small VITS text-to-speech checkpoints, one per language, covering over 1,100 languages. Price: free; non-commercial only; credit required; cannot ship inside an app.
Connect: download from https://huggingface.co/facebook/mms-tts-eng (no API).
Rule: Non-commercial use only (CC-BY-NC 4.0).
Rule: Credit Meta and link the license when you share the weights.
License: https://github.com/facebookresearch/fairseq/tree/main/examples/mms (checked 2026-10-25; details: https://agentgid.com/assets/mms-tts/)
Speech: Meta MMS-TTS (facebook/mms-tts), CC BY-NC 4.0, https://creativecommons.org/licenses/by-nc/4.0/Alternatives
Meta MMS-TTS This page
Pick Chatterbox for an MIT-licensed voice you may use in paid products, with voice cloning in 23 languages.
Pick Piper for a fast local voice engine whose downloadable voices each carry their own license, some fit for commercial use.
Pick OmniVoice when you need 600+ languages plus cloning a voice from a short clip.
Local desktop app for voice cloning, voice design, video dubbing, dictation and transcription in 646 languages, with a local API and an MCP server for agents.
Long-form multi-speaker TTS for podcast-style dialogue, up to 90 minutes and 4 speakers, in English and Chinese.
Questions
Can I use MMS-TTS voices in a paid app or a monetized video?
No. The code and the voice files are under CC BY-NC 4.0, which does not allow commercial use.
How do I get a voice for another language?
Each language has its own checkpoint named by its ISO 639-3 code; Meta publishes the list of codes for the 1107 languages.
Why does the same sentence sound slightly different each time?
The model picks speech rhythm with some randomness; set a fixed seed to get the same audio again.
Which software version do I need?
Hugging Face Transformers 4.33 or newer runs MMS-TTS.