{
 "slug": "mms-tts",
 "name": "Meta MMS-TTS",
 "author": "Meta (FAIR)",
 "density": "full",
 "status": "active",
 "status_note": null,
 "alternatives_page": null,
 "one_liner": "Family of small VITS text-to-speech checkpoints, one per language, covering over 1,100 languages.",
 "category": {
  "slug": "voiceover",
  "name": "Voiceover (text-to-speech)"
 },
 "tags": [
  "Open source"
 ],
 "styles": [],
 "logo_url": "https://agentgid.com/media/avatars/facebookresearch.png",
 "logo_letter": "M",
 "links": {
  "repo": "https://github.com/facebookresearch/fairseq",
  "website": "https://huggingface.co/facebook/mms-tts-eng",
  "api_docs": null
 },
 "preview": null,
 "verdicts": [
  {
   "key": "price",
   "label": "Price",
   "value": "Free",
   "status": "yes",
   "sub": "No paid plan",
   "quote": null,
   "note": "Open weights, free to download; self-hosted.",
   "source": {
    "label": "huggingface.co/facebook/mms-tts-eng",
    "url": "https://huggingface.co/facebook/mms-tts-eng"
   },
   "n": 1
  },
  {
   "key": "commercial",
   "label": "Commercial use",
   "value": "No",
   "status": "no",
   "sub": "CC-BY-NC-4.0",
   "quote": "The MMS code and model weights are released under the CC-BY-NC 4.0 license.",
   "note": "The license does not allow commercial use of the code or weights.",
   "source": {
    "label": "github.com/facebookresearch/fairseq/tree/main/examples/mms",
    "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms"
   },
   "n": 2
  },
  {
   "key": "credit",
   "label": "Credit the author",
   "value": "Required",
   "status": "cond",
   "sub": "Show a credit line",
   "quote": "The MMS code and model weights are released under the CC-BY-NC 4.0 license.",
   "note": "Speech: Meta MMS-TTS (facebook/mms-tts), CC BY-NC 4.0, https://creativecommons.org/licenses/by-nc/4.0/",
   "source": {
    "label": "github.com/facebookresearch/fairseq/tree/main/examples/mms",
    "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms"
   },
   "n": 3
  },
  {
   "key": "agent_access",
   "label": "Agent access",
   "value": "Download",
   "status": "info",
   "sub": "Files by hand",
   "quote": null,
   "note": "There is no package or API. Files are downloaded by hand from the official site.",
   "source": {
    "label": "github.com/facebookresearch/fairseq",
    "url": "https://github.com/facebookresearch/fairseq"
   },
   "n": 4
  }
 ],
 "license": {
  "name": "CC-BY-NC-4.0 (code and weights)",
  "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms",
  "summary": "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.",
  "pages_read": 1,
  "rules": [
   "Non-commercial use only (CC-BY-NC 4.0).",
   "Credit Meta and link the license when you share the weights."
  ],
  "rows": [
   {
    "label": "Commercial use",
    "value": "No",
    "status": "no",
    "quote": "The MMS code and model weights are released under the CC-BY-NC 4.0 license.",
    "source": {
     "label": "github.com/facebookresearch/fairseq/tree/main/examples/mms",
     "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms"
    },
    "note": null
   },
   {
    "label": "Credit",
    "value": "Required",
    "status": "cond",
    "quote": "The MMS code and model weights are released under the CC-BY-NC 4.0 license.",
    "source": {
     "label": "github.com/facebookresearch/fairseq/tree/main/examples/mms",
     "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms"
    },
    "note": null
   },
   {
    "label": "Inside your app or game",
    "value": "Not allowed",
    "status": "no",
    "quote": "The MMS code and model weights are released under the CC-BY-NC 4.0 license.",
    "source": {
     "label": "github.com/facebookresearch/fairseq/tree/main/examples/mms",
     "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms"
    },
    "note": null
   },
   {
    "label": "Pass the files on to your users",
    "value": "With conditions",
    "status": "cond",
    "quote": "provide a link to the license, and indicate if changes were made",
    "source": {
     "label": "creativecommons.org/licenses/by-nc/4.0",
     "url": "https://creativecommons.org/licenses/by-nc/4.0/"
    },
    "note": "Sharing the weights is allowed for non-commercial purposes with credit, a license link and a note of changes."
   },
   {
    "label": "Monetized YouTube",
    "value": "Not stated",
    "status": "unknown",
    "quote": "The MMS code and model weights are released under the CC-BY-NC 4.0 license.",
    "source": {
     "label": "github.com/facebookresearch/fairseq/tree/main/examples/mms",
     "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms"
    },
    "note": null
   },
   {
    "label": "AI training",
    "value": "Not stated",
    "status": "unknown",
    "quote": null,
    "source": null,
    "note": null
   },
   {
    "label": "Bots and bulk downloads",
    "value": "Not stated",
    "status": "unknown",
    "quote": null,
    "source": null,
    "note": null
   }
  ],
  "checked_at": "2026-10-25",
  "commercial_use_page": "https://agentgid.com/assets/mms-tts/commercial-use/"
 },
 "overview": {
  "heading": "Meta MMS-TTS: free speech voices for 1,100+ languages",
  "body": "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."
 },
 "uses": [
  {
   "title": "Speech in languages paid voices skip",
   "text": "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.",
   "idea": false,
   "image": null
  },
  {
   "title": "Audio files from a script",
   "text": "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.",
   "idea": false,
   "image": null
  },
  {
   "title": "Text in non-Latin scripts",
   "text": "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.",
   "idea": false,
   "image": null
  },
  {
   "title": "Faster or slower reading",
   "text": "Make the voice read faster or slower, for example slower for language learners. One setting changes the speed of the whole clip.",
   "idea": false,
   "image": null
  },
  {
   "title": "Read-aloud on a hobby site",
   "text": "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.",
   "idea": true,
   "image": null
  },
  {
   "title": "Try a language before buying a voice",
   "text": "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.",
   "idea": true,
   "image": null
  }
 ],
 "start": {
  "prompt": "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.",
  "install": "pip install --upgrade transformers accelerate",
  "install_note": null,
  "code": [
   {
    "tab": "Step 1",
    "intro": "Load the voice for your language by its code (facebook/mms-tts-<code>) and turn text into a waveform.",
    "source": "model = VitsModel.from_pretrained(\"facebook/mms-tts-eng\")\ntokenizer = AutoTokenizer.from_pretrained(\"facebook/mms-tts-eng\")"
   },
   {
    "tab": "Step 2",
    "intro": "Save the result as a WAV file at the model's sampling rate.",
    "source": "scipy.io.wavfile.write(\"techno.wav\", rate=model.config.sampling_rate, data=output.float().numpy())"
   }
  ]
 },
 "mistakes": [
  {
   "dont": "Using MMS-TTS voices in a paid app, an ad or a client project",
   "fix": "Use it only for research, teaching or hobby work; pick a commercially licensed voice (for example Chatterbox, MIT) for products",
   "why": "The weights are under a non-commercial license.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "write(\"out.wav\", rate, waveform.numpy()) with the (1, samples) tensor as is",
   "fix": "write(\"hello.wav\", sampling_rate, audio_data.squeeze())",
   "why": "The docs squeeze the batch dimension before saving, so the file holds one channel of audio.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "Generating twice and expecting identical audio",
   "fix": "Call set_seed(555) (any fixed number) before generating",
   "why": "VITS adds randomness to rhythm, so output changes between runs.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "Feeding Korean, Arabic or other non-Latin text without uroman installed",
   "fix": "pip install -U uroman, then check tokenizer.is_uroman",
   "why": "Those voices were trained on romanized text.",
   "dont_code": false,
   "fix_code": true
  },
  {
   "dont": "pip install --upgrade transformers with no version, as the model card shows",
   "fix": "Pin a tested Transformers version (4.33 or newer) in requirements",
   "why": "The model needs 4.33+, and an unpinned upgrade can change behaviour between runs of your project.",
   "dont_code": true,
   "fix_code": false
  }
 ],
 "agent": {
  "self_serve": false,
  "self_serve_text": null,
  "install": null,
  "repo": "https://github.com/facebookresearch/fairseq",
  "api_docs": null,
  "api_account": "Not needed. Everything runs on your side.",
  "get_files": null,
  "formats": [],
  "limits": null,
  "mcp": null,
  "mcp_url": null,
  "credit_line": "Speech: Meta MMS-TTS (facebook/mms-tts), CC BY-NC 4.0, https://creativecommons.org/licenses/by-nc/4.0/",
  "rules_text": "- 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.\n  Connect: download from https://huggingface.co/facebook/mms-tts-eng (no API).\n  Rule: Non-commercial use only (CC-BY-NC 4.0).\n  Rule: Credit Meta and link the license when you share the weights.\n  License: https://github.com/facebookresearch/fairseq/tree/main/examples/mms (checked 2026-10-25; details: https://agentgid.com/assets/mms-tts/)",
  "agent_md": "https://agentgid.com/assets/mms-tts/agent.md",
  "card_json": "https://agentgid.com/assets/mms-tts/card.json"
 },
 "popularity": {
  "gid_score": 46,
  "stars": 32204,
  "downloads_7d": null,
  "downloads_7d_label": null,
  "downloads_change_4w_pct": null,
  "eco": null,
  "package": null,
  "repo": "facebookresearch/fairseq",
  "agent_projects": null,
  "agent_projects_total": null,
  "downloads_unconfirmed": false,
  "series": {
   "downloads_weekly": [],
   "stars": [
    [
     "2026-11-07",
     32206
    ],
    [
     "2026-11-08",
     32207
    ],
    [
     "2026-11-09",
     32206
    ],
    [
     "2026-11-10",
     32203
    ],
    [
     "2026-11-11",
     32204
    ],
    [
     "2026-11-12",
     32207
    ],
    [
     "2026-11-13",
     32208
    ],
    [
     "2026-11-14",
     32206
    ],
    [
     "2026-11-15",
     32206
    ],
    [
     "2026-11-16",
     32205
    ],
    [
     "2026-11-17",
     32205
    ],
    [
     "2026-11-18",
     32205
    ],
    [
     "2026-11-19",
     32204
    ]
   ]
  },
  "stars_flat_since": null,
  "updated_at": "2026-11-19"
 },
 "alternatives": [
  {
   "slug": "mms-tts",
   "name": "Meta MMS-TTS",
   "why": null,
   "current": true,
   "price": "Free",
   "commercial": {
    "value": "Non-commercial",
    "status": "no"
   },
   "access": "Download"
  },
  {
   "slug": "chatterbox",
   "name": "Chatterbox",
   "why": "Pick Chatterbox for an MIT-licensed voice you may use in paid products, with voice cloning in 23 languages.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "Commercial OK",
    "status": "yes"
   },
   "access": "PyPI"
  },
  {
   "slug": "piper",
   "name": "Piper",
   "why": "Pick Piper for a fast local voice engine whose downloadable voices each carry their own license, some fit for commercial use.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "PyPI"
  },
  {
   "slug": "omnivoice",
   "name": "OmniVoice",
   "why": "Pick OmniVoice when you need 600+ languages plus cloning a voice from a short clip.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "Non-commercial",
    "status": "no"
   },
   "access": "PyPI"
  },
  {
   "slug": "voicestudio",
   "name": "VoiceStudio",
   "why": "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.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "MCP, API"
  },
  {
   "slug": "vibevoice",
   "name": "VibeVoice",
   "why": "Long-form multi-speaker TTS for podcast-style dialogue, up to 90 minutes and 4 speakers, in English and Chinese.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "Download"
  }
 ],
 "faq": [
  {
   "q": "Can I use MMS-TTS voices in a paid app or a monetized video?",
   "a": "No. The code and the voice files are under CC BY-NC 4.0, which does not allow commercial use."
  },
  {
   "q": "How do I get a voice for another language?",
   "a": "Each language has its own checkpoint named by its ISO 639-3 code; Meta publishes the list of codes for the 1107 languages."
  },
  {
   "q": "Why does the same sentence sound slightly different each time?",
   "a": "The model picks speech rhythm with some randomness; set a fixed seed to get the same audio again."
  },
  {
   "q": "Which software version do I need?",
   "a": "Hugging Face Transformers 4.33 or newer runs MMS-TTS."
  }
 ],
 "at_a_glance": {
  "latest_version": "5.22.2",
  "last_release": "2022-06-27",
  "last_commit": "2025-09-30",
  "runtime": "Transformers 4.33+ with PyTorch; Python 3.11+ for the current release (5.22.2, latest checked); uroman for languages in non-Latin scripts. No demo was run.",
  "key_needed": false
 },
 "good_to_know": [
  "No commercial use: the code and the voice files are under a non-commercial license.",
  "The same text can sound a little different each run. Set a fixed seed when you need the exact same audio again.",
  "There is one voice per language, so you cannot pick between several voices or clone your own from these files alone.",
  "The original Meta code project is archived and read-only, so expect no new fixes there; the Transformers version is the easier path.",
  "Languages in non-Latin scripts need the extra uroman package before the text goes in."
 ],
 "stack_snippets": [],
 "claims": [
  "Text-to-speech models for over 1,100 languages",
  "The facebook/mms-tts collection page lists 1107 languages"
 ],
 "checked": {
  "license_read": "2026-10-25",
  "overview_checked": "2026-11-10",
  "numbers_updated": "2026-11-19",
  "sources": [
   {
    "label": "huggingface.co/facebook/mms-tts-eng",
    "url": "https://huggingface.co/facebook/mms-tts-eng"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/facebook/mms-tts-eng/raw/main/README.md"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/api/models/facebook/mms-tts-eng/tree/main"
   },
   {
    "label": "huggingface.co/facebook/mms-tts",
    "url": "https://huggingface.co/facebook/mms-tts"
   },
   {
    "label": "README on GitHub",
    "url": "https://github.com/facebookresearch/fairseq/blob/main/examples/mms/README.md"
   },
   {
    "label": "github.com/facebookresearch/fairseq",
    "url": "https://github.com/facebookresearch/fairseq"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/docs/transformers/model_doc/vits"
   },
   {
    "label": "creativecommons.org/licenses/by-nc/4.0",
    "url": "https://creativecommons.org/licenses/by-nc/4.0/"
   },
   {
    "label": "pypi.org/pypi/transformers/json",
    "url": "https://pypi.org/pypi/transformers/json"
   },
   {
    "label": "github.com/facebookresearch/fairseq/tree/main/examples/mms",
    "url": "https://github.com/facebookresearch/fairseq/tree/main/examples/mms"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/api/models/facebook/mms-tts-eng"
   }
  ],
  "unverified": "Download and like counts are for the English checkpoint only, not the whole family. The fairseq repo is archived (read-only) on GitHub."
 },
 "user_reports": null,
 "url": "https://agentgid.com/assets/mms-tts/",
 "note": "Written by AgentGid from the official pages in checked.sources; quotes are copied from those pages. status: yes | cond | no | unknown | info. Prices and vendor claims are as reported on the checked date. Not legal advice."
}
