---
title: "Phonon-2.5 vs Meta Muse Voice Transcribe"
description: "Muse Voice Transcribe: 4.93 % English word error; Phonon-2.5: 5.06 %; Phonon-2.5 English: 4.82 %. Muse is a $0.18 an hour API; Phonon runs on your hardware."
canonical: "https://www.fermionresearch.com/models/phonon-2-5/vs-meta-muse/"
source: "Fermion Research"
---

Phonon/facts checked 13 November 2026

# Phonon-2.5 vs Meta Muse Voice Transcribe

On the leaderboard's English sets the three are close: Muse is just ahead of the 25-language Phonon-2.5 and just behind Phonon-2.5 English. The bigger differences are hosting and features.

[Phonon-2.5 downloads and benchmarks](https://www.fermionresearch.com/models/phonon-2-5/)

## The short answer

On the Open ASR Leaderboard's seven English sets, Meta Muse Voice Transcribe averages 4.93 % word error, a little lower than Phonon-2.5 (5.06 %) and a little higher than Phonon-2.5 English (4.82 %). Choose Muse if you want a hosted streaming API with speaker attribution; choose Phonon when you need the model on your own hardware, offline, or without an hourly fee.

The set-by-set picture splits cleanly: Phonon is lower on LibriSpeech and AMI meetings, Muse is lower on earnings calls, GigaSpeech, SPGISpeech and VoxPopuli.

## Side by side

Meta facts from Meta's model page (dev.meta.ai/models/muse-voice-transcribe), read 2026-11-13.

|  | Phonon-2.5 | Meta Muse Voice Transcribe |
| --- | --- | --- |
| Model type | Open weights on Hugging Face | Hosted API (Meta Model API), model ID muse-voice-transcribe-1.0 |
| Size | 156 MB download (Phonon-2.5 English: 158 MB) | Not published |
| Languages | 25 European languages (Phonon-2.5 English: English only) | Not listed on Meta's model page |
| English word error, seven Open ASR sets | 5.06 % (Phonon-2.5 English: 4.82 %) | 4.93 % |
| Price per audio hour | No per-hour fee when self-hosted | $0.18 ($3.00 per 1,000 minutes) |
| Where it runs | Your hardware: CPUs (Linux x86-64 and arm64, Windows x86-64), Apple silicon, NVIDIA GPUs, Android | Meta's cloud |
| Streaming | Yes, live WebSocket from fermion serve | Yes, with end-of-speech detection in the model |
| Diarization | No | Speaker attribution for 20+ speakers |
| Word timestamps | Yes (--json output) | Not stated on Meta's model page |

## English, set by set

Phonon-2.5 and Phonon-2.5 English are lower on LibriSpeech clean, LibriSpeech other and AMI. Muse is lower on Earnings-22, GigaSpeech, SPGISpeech and VoxPopuli.

| Test set | Phonon-2.5 | Phonon-2.5 English | Meta Muse Voice Transcribe |
| --- | --- | --- | --- |
| LibriSpeech clean | 1.60 | 1.64 | 1.84 |
| LibriSpeech other | 3.41 | 3.56 | 4.51 |
| AMI | 9.12 | 8.76 | 9.20 |
| Earnings-22 | 6.72 | 6.22 | 6.01 |
| GigaSpeech | 8.04 | 7.99 | 7.75 |
| SPGISpeech | 3.31 | 3.31 | 3.21 |
| VoxPopuli | 3.23 | 2.28 | 2.02 |
| Average of the seven | 5.06 | 4.82 | 4.93 |

## Where Muse Voice Transcribe is the better choice

- Live conversations with several people: speaker attribution for 20 or more speakers and end-of-speech detection inside the recognition model.
- Contextual and keyword biasing for custom vocabulary.
- Earnings calls, podcasts and parliamentary audio, where its per-set scores are lower.
- An API that Meta says works with OpenAI-SDK-compatible clients.

## Where Phonon-2.5 is the better choice

- English accuracy with Phonon-2.5 English: a lower seven-set average (4.82 % against 4.93 %).
- Read speech and meetings: lower word error on LibriSpeech and AMI.
- Your hardware, your network: a 156 MB model that runs offline on CPUs, Macs, NVIDIA GPUs and Android.
- No hourly fee, and the same OpenAI-shaped route (POST /v1/audio/transcriptions) from fermion serve.

```text
pip install fermion-research
fermion transcribe phonon-2.5 interview.wav --json
fermion serve phonon-2.5   # POST /v1/audio/transcriptions, GET /v1/audio/stream
```

## Questions

## Related

- [Phonon-2.5 vs ElevenLabs Scribe](https://www.fermionresearch.com/models/phonon-2-5/vs-elevenlabs-scribe/)
- [Phonon-2.5 English](https://www.fermionresearch.com/models/phonon-2-5-english/)
- [Speech streaming docs](https://www.fermionresearch.com/docs/speech-streaming/)
- [English benchmark results](https://www.fermionresearch.com/speech/english-benchmark-results/)

## Sources and method

- Muse model ID, price, speaker attribution, streaming and biasing: dev.meta.ai/models/muse-voice-transcribe, read 2026-11-13.
- Rival English word error: Open ASR Leaderboard, seven English sets, snapshot 2026-09-25 (huggingface.co/spaces/hf-audio/open_asr_leaderboard).
- Phonon-2.5 and Phonon-2.5 English: Fermion Research measurement, Phonon-2.5 release post (2026-10-22), Open ASR Leaderboard scoring code, full test sets of the same seven sets.

Canonical: https://www.fermionresearch.com/models/phonon-2-5/vs-meta-muse/

Source: [https://www.fermionresearch.com/models/phonon-2-5/vs-meta-muse/](https://www.fermionresearch.com/models/phonon-2-5/vs-meta-muse/)
