Is Scribe v3 state of the art?Pending benchmarks.Announced Nov 10, 2026; no independent results yet.
ElevenLabs' speech-to-text model for recorded audio, announced November 10, 2026. Available in ElevenAPI as scribe_v3, and it is a default in the ElevenLabs app alongside Scribe v3 Live. Features include speaker diarization (up to 32 speakers), number formatting, language hints, keyterm prompting, entity detection, transcript editing and word-level timestamps. No public weight release is stated.
The details so far
- Lab
- ElevenLabs
- Announced
- Nov 10, 2026
- API
- Live · scribe_v3
- Open weights
- Closed · No public weight release stated
- Type
- Speech-to-text model for recorded (batch) audio; not the realtime Scribe v3 Live model (ElevenLabs blog and docs)
- Hosted access
- ElevenAPI as scribe_v3. Official blog: both Scribe v3 and Scribe v3 Live are the default in the ElevenLabs app (ElevenLabs blog and docs)
- Languages
- Official docs list 90+ languages. The launch blog reports results across 102 languages on an internal version of FLEURS (ElevenLabs blog and Speech to Text docs)
- Features
- Speaker diarization for up to 32 speakers, numbers as digits or words, secondary language codes for mixed-language audio, keyterm prompting (up to 1,000 terms), entity detection, transcript editing, and word-level timestamps (ElevenLabs docs)
- Limits
- Files up to 5 GB; standard mode up to 15 hours (Speech to Text docs)
- Pricing
- Official ElevenAPI price: $0.20 per hour of audio, including silence. Keyterm prompting $0.05 per hour and transcript editing $0.07 per hour on the public pricing table (ElevenLabs API pricing)
- Deployment
- Runs in the US by default; isolated EU, India and Singapore environments for enterprise customers with data residency requirements. Zero Retention Mode, SOC 2, ISO 27001 and PCI DSS Level 1 coverage, and HIPAA-eligible with a Business Associate Agreement, are stated on the launch blog; private deployment is also offered (ElevenLabs blog)
- License
- Not stated; no public weights
- Related
- Separate from Scribe v3 Live (the realtime model), Scribe v2, Scribe v2 Realtime, Cue and Eleven Realtime
Tags marked unsure are not stated on the lab's own pages.
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
What the lab claims
Self-reported. Shown for context; not used in any verdict.
Lab claim: self-reported 27% fewer word errors than Scribe v2 across 102 languages on an internal version of FLEURS, with an improvement in every language tested (ElevenLabs blog and API pricing page).
Lab claim: self-reported 12% fewer diarization errors than Scribe v2 overall and 17% fewer on recordings with three or more speakers, on ElevenLabs' own 16-language dataset of meetings, agent calls and voice notes (ElevenLabs blog).
Sources
LABIntroducing Scribe v3 and v3 Live (ElevenLabs blog)elevenlabs.io/blog/scribe-v3 · Nov 10, 2026LABElevenLabs docs: Speech to Textelevenlabs.io/docs/overview/capabilities/speech-to-textLABElevenAPI pricingelevenlabs.io/pricing/apiLABElevenLabs Speech to Text product pageelevenlabs.io/speech-to-textLABElevenLabs on X: Scribe v3x.com/ElevenLabs/status/2120217467100541396 · Nov 10, 2026LABElevenLabs developers on X: Scribe v3x.com/ElevenLabsDevs/status/2120219053046595748 · Nov 10, 2026Tracking continues until an independent board lists it.