# Muse Voice Transcribe Benchmark Scores & Performance

> Muse Voice Transcribe has Meta launch evaluation results. Voice evidence is display-only and does not produce a text-model score.

Canonical page: https://benchlm.ai/models/muse-voice-transcribe

Last updated: October 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Meta |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | N/A |
| Official model card | [Meta model documentation](https://research.meta.ai/blog/introducing-muse-voice-transcribe) |
| Overall Score | Not scored (voice evidence only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Muse Voice Transcribe
- Variant: base
- Benchmarks covered: 0 of 639
- Coverage note: Speech and voice results appear below; no weighted text-model benchmark rows are stored.

## Speech and voice evidence

[Muse Voice Transcribe launch evaluation](/voice-benchmarks/muse-voice-transcribe-evaluation)

These are provider-reported launch results, not an independent end-to-end voice-agent ranking. The post does not publish enough per-dataset detail to reconstruct either aggregate from raw runs.

| Metric | Result |
| --- | --- |
| Streaming WER rank | #1 of 8 |
| Streaming WER | 3.1% |
| Time to final transcript | About 0.16s |
| Diarization rank | #1 of 6 |
| Average diarization error | 17.5% |
| Validated languages | 25 |
| Speaker diarization | 20+ speakers |

Provider launch snapshot · September 1, 2026 · lower WER and diarization error are better

- [Evaluation source](https://research.meta.ai/blog/introducing-muse-voice-transcribe)

Available through Meta Model API, Meta AI for Mac, and Muse Code as of September 1, 2026.

## Other Meta Models

- [Muse Wonder Full](/models/muse-wonder-full) - Score: 74.27
- [Muse Wonder](/models/muse-wonder) - Score: 71.16
- [Muse Spark 1.1](/models/muse-spark-1-1) - Score: 66.02
- [Muse Spark 1.2](/models/muse-spark-1-2) - Score: 65.84
- [Muse Spark Open](/models/muse-spark-open) - Score: 62.66
- [Muse Spark](/models/muse-spark) - Score: 60.47
- [Muse Glimmer 30B](/models/muse-glimmer-30b) - Score: 41.19
- [Llama 3.1 405B](/models/llama-3-1-405b) - Score: 28.21
- [Llama 4 Scout](/models/llama-4-scout) - Score: 28.2
- [Llama 4 Maverick](/models/llama-4-maverick) - Score: 21.61
- [Llama 3 70B](/models/llama-3-70b) - Score: 21.32
- [Muse Spark 1.3](/models/muse-spark-1-3) - Score: not computed
- [Llama 3.3 70B](/models/llama-3-3-70b) - Score: not computed
- [Llama 3.1 70B](/models/llama-3-1-70b) - Score: not computed
- [Llama 3.1 8B](/models/llama-3-1-8b) - Score: not computed
- [Llama 4 Behemoth](/models/llama-4-behemoth) - Score: not computed