# facebookresearch/seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

Repository: https://github.com/facebookresearch/seamless_communication
Canonical: https://ross.abutalabs.com/products/seamless_communication
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2026-07-28T13:03:12+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 35, longevity 80
- inputs: {"age_days": 1128, "days_push": 36, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11842, forks 1175 (observed 2026-08-28T04:10:50.193955+00:00)

## What it is
A library of foundational multilingual multimodal AI models from Meta for speech and text translation, including SeamlessM4T, SeamlessExpressive, and SeamlessStreaming. It supports translation across roughly 100 languages with speech-to-text, text-to-speech, and streaming capabilities.

## Use cases
- translate speech between 100 languages
- build real-time simultaneous translation
- preserve voice style and prosody across languages
- transcribe streaming audio with multilingual ASR
- run speech-to-speech translation models locally
- experiment with multilingual foundation models in notebooks

## When to choose
- you need state-of-the-art multilingual speech or text translation
- you want expressive translation that preserves prosody and voice
- you need streaming/simultaneous translation with low latency
- you want to fine-tune or research multimodal translation models

## When to avoid
- you need a lightweight production translation API without GPU resources
- you only need simple text-to-text translation of a few languages
- you require a permissively licensed model for commercial redistribution without checking the custom license

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, speech-recognition, nlp, llm-inference
- domain: speech-processing, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: speech-translation, multilingual, seamlessm4t, text-to-speech, simultaneous-translation, meta-ai, foundation-models, natural-language-processing, gpu

## Member repositories
- facebookresearch/seamless_communication (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:50.193955+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:15:16.842152+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/seamless_communication (fetched 2026-08-28T04:10:50.193955+00:00, sha 93ab8e072a7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.