ElevenLabs · Chat
Scribe v3 Live
ElevenLabs' most accurate realtime speech-to-text model, with turn prediction across 90+ languages.
Evidence and sources
Released 9 Nov 2026Maker HQ: US (according to ElevenLabs's own website)
Sources: LLMGateway data, llminfo researchPrimary data from LLMGateway
from llminfo research: release date
Input & output
from the model's typeText
Text
Capabilities
Supported operations and provider-stated features
Function calling
Listings
We don't have any priced listings for this model yet.
1 listing without a price is hidden.
Benchmarks
No benchmark scores yet.
Around the web
- ElevenLabs — Meet Scribe the world's most accurate ASR model
Scribe is engineered for precision. In FLEURS & Common Voice benchmark tests across 99 languages, …
Scribe is engineered for precision. In FLEURS & Common Voice benchmark tests across 99 languages, it consistently outperforms leading models like Gemini 2.0 Flash, Whisper Large V3 and Deepgram Nova-…elevenlabs.io
- ElevenLabs is launching its own speech-to-text model
Scribe currently only works with pre-recorded audio formats. The company said it will release a …
Scribe currently only works with pre-recorded audio formats. The company said it will release a low-latency real-time version of the model soon. That means it is not yet effective for meeting transcr…finance.yahoo.com
- ElevenLabs Scribe v3 Live uses conversational context to stop voice agents from cutting off callers mid-sentence
Elevenlabs has released Scribe v3 and Scribe v3 Live, two speech recognition models built for …
Elevenlabs has released Scribe v3 and Scribe v3 Live, two speech recognition models built for messy audio situations like crosstalk and background noise, covering both pre-recorded files and real-tim…the-decoder.com
- ElevenLabs Scribe v2: Features, Accuracy & Pricing
Scribe v2 is the batch and long-form member of ElevenLabs' speech-to-text family. It is designed …
Scribe v2 is the batch and long-form member of ElevenLabs' speech-to-text family. It is designed for recordings such as interviews, podcasts, research sessions, training media, calls, and subtitle wo…therundown.ai
- Transcription (STT) API - ElevenLabs
Scribe v2 achieves best-in-class accuracy across 99 languages and is robust to challenging audio conditions, …
Scribe v2 achieves best-in-class accuracy across 99 languages and is robust to challenging audio conditions, accents, and recording quality. It outperforms previous generation models and other leadin…elevenlabs.io
- Scribe v2 - Speech-to-Text API Pricing | OpenRouter
ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level …
ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging. ### Where is the Scribe v2 do…openrouter.ai
- Scribe v2: Accurate batch transcription and subtitling
Scribe v2 is now used in ElevenLabs Studio for more accurate subtitles, captions and transcriptions, …
Scribe v2 is now used in ElevenLabs Studio for more accurate subtitles, captions and transcriptions, supporting teams that manage large libraries of audio and video across marketing, media, research,…elevenlabs.io
- Introducing Scribe v3 and v3 Live, our most accurate speech to text models
ElevenLabs evaluated both models against Scribe v2, Scribe v2 Realtime, and other popular Speech to …
ElevenLabs evaluated both models against Scribe v2, Scribe v2 Realtime, and other popular Speech to Text models, scoring each on the same datasets. Multilingual accuracy was measured on an internal v…elevenlabs.io
- ElevenLabs Scribe v2 — Speech-to-text on Replicate
### elevenlabs/scribe-v2 elevenlabs / scribe-v2 Transcribe speech with ElevenLabs Scribe v2. 90+ languages, word-level timestamps, …
### elevenlabs/scribe-v2 elevenlabs / scribe-v2 Transcribe speech with ElevenLabs Scribe v2. 90+ languages, word-level timestamps, speaker diarization for up to 32 speakers, audio event tagging, and …replicate.com
- ElevenLabs Scribe V2 vs. AssemblyAI | Speech-to-Text
: Yes, on comparable workloads. AssemblyAI is $0.21/hour pre-recorded and from $0.15/hour real-time. Scribe V2 …
: Yes, on comparable workloads. AssemblyAI is $0.21/hour pre-recorded and from $0.15/hour real-time. Scribe V2 batch starts at $0.22/hour but climbs to ~$0.34/hour once you turn on entity detection (…assemblyai.com
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works