Public KG record
Muse Voice Transcribe
Recorded overview
An autoregressive multimodal model performing streaming ASR, diarization for 20+
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: first place on Artificial Analysis for streaming speech-to-text
- Benchmarks: first place on public diarization benchmarks
- Benchmarks: AA-WER Streaming
- Capabilities: Adaptive delay
- Deployment: hosted API on Meta Model API
- Integrations: Meta Model API
- Languages: 70+ languages, 25 extensively verified and recommended at launch
- Languages: 70多种训练语言、25种验证语言
Evidence coverage
The KG currently records 15 known information dimensions and has 4 undocumented dimensions, linked to 2 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Meta — develops
- Cartesia Ink-2 — competes with
- Deepgram Flux — competes with
- ElevenLabs Scribe v2 Realtime — competes with
- Muse Code — applied to