Seamless Communication (SeamlessM4T, SeamlessExpressive)
Source: https://github.com/facebookresearch/seamless_communication
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Meta's SeamlessM4T family: speech-to-speech, speech-to-text, text-to-speech and text-to-text translation across nearly 100 languages, plus SeamlessExpressive (prosody-preserving). Core research option for localization/dubbing; license is non-commercial.",
"source_type": "repository",
"availability": "available",
"source_owner": "Meta FAIR",
"next_check_at": "2026-10-24T00:00:00.000Z",
"known_limitations": [
"Non-commercial license for code in this repository."
],
"upstream_updated_at": "2026-09-08T12:22:24.000Z"
}Evidence claims
- [upstream_claim] README: SeamlessM4T is an all-in-one massively multilingual multimodal translation model for speech and text in nearly 100 languages (S2ST, S2TT, T2ST, T2TT); it is the foundation for SeamlessExpressive. · locator: README, Intro source
- [sourced_fact] Repository LICENSE file is the Creative Commons Attribution-NonCommercial 4.0 International text (GitHub reports NOASSERTION). · locator: LICENSE, header source
- [sourced_fact] README links Hugging Face demo spaces (SeamlessM4T v2, SeamlessExpressive) and the seamless-m4t-v2-large model card. · locator: README, demo table source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | CC-BY-NC-4.0 | restricted | restricted | restricted | unknown | Non-commercial per LICENSE; commercial use not permitted by this text. |
| model_weights | unknown | unknown | unknown | unknown | unknown | Weights model card license was not fetched; assume non-commercial only after checking. |