whatmodel.sh / stt / Muse Voice Transcribe 1.0
Muse Voice Transcribe 1.0
↗ share
+ contribute
Muse Voice Transcribe 1.0 is a closed-weights speech-to-text model from Meta, released September 2026. Licence: proprietary.
Catalogue identity notes
Meta Superintelligence Labs' streaming ASR + diarization + endpointing model on the Meta Model API, exact API model string muse-voice-transcribe-1.0 (Meta pricing table). Launched 2026-09-01 per Meta's developer blog (dated Sep 3, 2026: 'This week, Meta launched ... Muse Voice Transcribe, on Meta Model API'). Closed weights. Pipecat benchmarked exactly model='muse-voice-transcribe-1.0' (MetaSTTService) on 2026-09-11.
Score within the Open ASR English short-form WER (March 2026) comparison set only.
$ how it compares
The speech-to-text models ranked either side of Muse Voice Transcribe 1.0, out of 176 with a score, then more from Meta.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 1 | Muse Voice Transcribe 1.0 | 71±3 | api $0.0030/audio min | ||
| 2 |  Grok Voice Transcribe 2.0 | 70±3 | api $0.0017/audio min | ||
| 3 |  Saarika v2.5 | 70±5 | comparison only | ||
| 4 |  Universal-3.6 Pro Realtime | 70±3 | api $0.0075/audio min | ||
| 5 |  Linden 1 (Agent STT) | 69±3 | api $0.0050/audio min | ||
| more from Meta | |||||
| 58 | Omnilingual ASR LLM 7B | 58±2 | local | ||
| 59 | Omnilingual ASR LLM 7B v2 | 58±3 | local | ||
| 62 | Omnilingual ASR LLM 3B | 57±2 | local | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 96% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Pipecat STT Benchmark · pooled semantic WER (1000 smart-turn samples, Sonnet 5.5 judge) | 0.7% ✎ | ▃·▃▅·▅▅·▃▅██ beats 16/16 | 96% |
$ where to run it
Through an API
api · $0.0030/audio min · developer.meta.com ↗ · price sourceUSD per input audio minute: Meta's model page pricing table lists muse-voice-transcribe-1.0 at $3.00 per 1,000 min / $0.18 per hour (÷1000). Product: Meta Model API speech-to-text (streaming wss://api.meta.ai/v1/asr/realtime and file https://api.meta.ai/v1/asr/transcribe). API model: muse-voice-transcribe-1.0. Price basis: published list rate. Currency: USD. Meta official model page, observed 2026-10-09.
$ how the score was worked out · Pipecat STT Benchmark · seman… 96%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README) | 1 | 96% |
| prior · pull toward the middle | 4% | |
| weighted average | = 71.0 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json