muse-voice-transcribe-1.0 ↗
$0.18
- Inference provider
- meta
- Platform
- Meta Model API
- Unit
- hour
- Currency
- USD
- Billing conditions
- rounding
- down_to_whole_seconds
- streaming_price_parity
- true
- Billing label
- Per processed audio hour
Muse Voice Transcribe 1.0 is a synchronous speech-to-text model from Meta. It is suited for push-to-talk, endpointing, and speaker-aware transcription, with keyword biasing for domain terms and langu…
meta/muse-voice-transcribe-1.0-20260903
Muse Voice Transcribe 1.0 is a synchronous speech-to-text model from Meta. It is suited for push-to-talk, endpointing, and speaker-aware transcription, with keyword biasing for domain terms and language biasing through language-name hints. It accepts mono 16-bit PCM WAV audio at 16 kHz or 24 kHz for recordings up to 10 minutes. It does not provide word-level timestamps or confidence scores, and other audio formats must be converted to WAV before upload.
1–2 / 2
$0.18
$0.0001
1–1 / 1
1–1 / 1
31 / 100
1–7 / 7
1–3 / 3
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.