As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/omnilingual-asr/

# Omnilingual ASR

Meta. Status: current. Type: speech and audio. Released: 2025-11-10.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| GitHub (fairseq2 checkpoints) | `omniASR_LLM_7B_v2` |  | https://github.com/facebookresearch/omnilingual-asr |
| Hugging Face (demo space and dataset) |  |  | https://huggingface.co/facebook |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## Where it stands

- Newer speech and audio models in the registry since its release: 79. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- After it from Meta: Muse Voice Transcribe 1.0 (2026-09-03) https://postcutoff.com/m/muse-voice-transcribe-1-0/
- Weights are public under a permissive licence (Apache-2.0).

## What stands out

- ASR for 1,600+ languages (first): Transcribes 1,600+ languages, ~500 of them never before supported by any ASR system (Whisper covers 99). Source: https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/
- Zero-shot in-context language extension: omniASR_LLM_7B_ZS transcribes new languages from a few paired audio-text examples at inference, extending potential coverage to 5,400+ languages. Source: https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/

## Notes

Open (Apache 2.0) suite: CTC and LLM-ASR models at 300M/1B/3B/7B, v2 checkpoints and 'Unlimited' long-audio LLM-ASR variants added December 2025, plus a 7B wav2vec 2.0 speech encoder and a corpus covering 350+ underserved languages. Checkpoints download via fairseq2 (e.g. https://dl.fbaipublicfiles.com/mms/omniASR-LLM-7B-v2.pt). Successor to MMS. The 'first' claim is Meta's ('never previously supported by any ASR model').

Meta's open massively multilingual speech recognition (Nov 2025, still Meta's current open ASR).

Sources: https://github.com/facebookresearch/omnilingual-asr · https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/

Model page: https://postcutoff.com/m/omnilingual-asr/