{"id":"elevenlabs-scribe-v3","slug":"elevenlabs-scribe-v3","name":"Scribe v3","orgId":"elevenlabs","family":"elevenlabs-scribe-v3","releaseDate":null,"availability":"ga","openWeights":false,"license":"Not stated; no public weights","paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://elevenlabs.io/blog/scribe-v3","hfRepo":null,"modalities":["audio"],"aliases":["Scribe v3","elevenlabs-scribe-v3","scribe v3","ElevenLabs Scribe v3","elevenlabs scribe v3","scribe_v3","scribe-v3"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-10","announced":"2026-11-10","blurb":"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.","api":"live","apiModelId":"scribe_v3","openWeights":"no","facts":[{"label":"Type","value":"Speech-to-text model for recorded (batch) audio; not the realtime Scribe v3 Live model (ElevenLabs blog and docs)"},{"label":"Hosted access","value":"ElevenAPI as scribe_v3. Official blog: both Scribe v3 and Scribe v3 Live are the default in the ElevenLabs app (ElevenLabs blog and docs)"},{"label":"Languages","value":"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)"},{"label":"Features","value":"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)"},{"label":"Limits","value":"Files up to 5 GB; standard mode up to 15 hours (Speech to Text docs)"},{"label":"Pricing","value":"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)"},{"label":"Deployment","value":"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)"},{"label":"Weights","value":"No public weight release stated"},{"label":"License","value":"Not stated; no public weights"},{"label":"Related","value":"Separate from Scribe v3 Live (the realtime model), Scribe v2, Scribe v2 Realtime, Cue and Eleven Realtime"}],"claims":["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":[{"kind":"lab","title":"Introducing Scribe v3 and v3 Live (ElevenLabs blog)","url":"https://elevenlabs.io/blog/scribe-v3","date":"2026-11-10"},{"kind":"lab","title":"ElevenLabs docs: Speech to Text","url":"https://elevenlabs.io/docs/overview/capabilities/speech-to-text"},{"kind":"lab","title":"ElevenAPI pricing","url":"https://elevenlabs.io/pricing/api"},{"kind":"lab","title":"ElevenLabs Speech to Text product page","url":"https://elevenlabs.io/speech-to-text"},{"kind":"lab","title":"ElevenLabs on X: Scribe v3","url":"https://x.com/ElevenLabs/status/2120217467100541396","date":"2026-11-10"},{"kind":"lab","title":"ElevenLabs developers on X: Scribe v3","url":"https://x.com/ElevenLabsDevs/status/2120219053046595748","date":"2026-11-10"}],"firstBenchmark":null},"organization":{"id":"elevenlabs","name":"ElevenLabs","slug":"elevenlabs","country":null,"url":null,"color":"#5B5B5B","mark":"11"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 10, 2026; no independent results yet.","lead":"As of Nov 22, 2026, Scribe v3 is pending benchmarks on isitsota: announced Nov 10, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}