Scribe v2 Realtime
Launched 2025-11-11; claims 93.5% accuracy across 30 European and Asian languages (company figure). EU and India data residency, zero-retention mode.
- Input
- audio
- Output
- text
- License
- proprietary
- Pricing
- per hour: $0.39 (per hour of audio (API)) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| ElevenLabs API (WebSocket) | scribe_v2_realtime | wss://api.elevenlabs.io/v1/speech-to-text/realtime | docs |
Notable capabilities (2)
- ~150 ms streaming STT with next-word prediction: Under 150 ms transcription latency with 'negative latency' next-word and punctuation prediction; VAD, manual commit, mid-conversation language switching; 90+ languages; PCM 48 kHz and u-law. source
- Realtime entity detection (found after launch): Entity detection added to realtime transcription on 2026-08-03. source
Sources: https://elevenlabs.io/docs/models , https://elevenlabs.io/pricing/api , https://elevenlabs.io/blog/introducing-scribe-v2-realtime
Other ElevenLabs models
Eleven v4 / Eleven v4 Turbo · Eleven Music v2.5 · Eleven v3 Conversational · Scribe v2 / Scribe v2 Medical · Eleven Sound Effects v2 · Eleven v3 · Eleven Flash v2.5 / Flash v2 · Eleven Multilingual v2 · Eleven Multilingual STS v2 (Voice Changer) · Eleven Voice Design v3 (Text to Voice) · Eleven Dubbing v2 · Scribe v1 · Eleven Turbo v2.5 / Turbo v2