Fermion ResearchMeta Superintelligence LabsAudio matchupSpeech to text
Phonon-2vs.Muse Voice Transcribe
Which model is better?
Muse Voice Transcribe is slightly ahead in independent tests, but the lead is not certain.
Pick Phonon-2 for
Pick Muse Voice Transcribe for
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
Hugging Face Open ASR
Muse Voice Transcribe slightly aheadMuse Voice Transcribe is clearly ahead in 0 of 9 subtests and slightly in 8, Phonon-2 in none. 1 is level.
Open ASR English short-form WER: Voxpopuli-AA-Cleaned
lower is better, as of October 28, 2026
Open ASR English short-form WER: Voice Arena Monsoon
lower is better, as of October 28, 2026
Open ASR English short-form WER: Earnings22-Cleaned-AA-chunked
lower is better, as of October 28, 2026
Show all 9 subtests
| Subtest | Phonon-2 | Muse Voice Transcribe | Verdict |
|---|---|---|---|
| Open ASR English short-form WER: Voxpopuli-AA-Cleaned (lower is better) | 2.5 % | 2.0 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: Voice Arena Monsoon (lower is better) | 4.9 % | 4.2 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: Earnings22-Cleaned-AA-chunked (lower is better) | 7.0 % | 6.0 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: Private (scripted) (lower is better) | 5.2 % | 4.5 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: URGENT24 (lower is better) | 14.9 % | 13.0 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: Average WER (11-set macro-average) (lower is better) | 6.9 % | 6.3 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: Private (conversational) (lower is better) | 14.1 % | 13.0 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: Gigaspeech-Cleaned (lower is better) | 8.4 % | 7.8 % | Muse Voice Transcribe slightly ahead |
| Open ASR English short-form WER: AMI-Cleaned (lower is better) | 9.3 % | 9.2 % | level |
Source · latest October 28, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| Phonon-2 | Muse Voice Transcribe | |
|---|---|---|
| Task | Speech to text | Speech to text |
| Developer | Fermion Research | Meta Superintelligence Labs |
| Status | Open weights | Active |
| Released | n/a | September 1, 2026 |
| Weights | open | n/a |
| Runs locally | yes | no |
| License | CC-BY-4.0 | n/a |
| Price | n/a | $0.18 per audio hour ($3 per 1,000 audio minutes) |
| Popularity (out of 100) | 44 | 0 |