ElevenLabs guide: building meeting transcription with Scribe v2 and Realtime APIs
Overview
ElevenLabs, in a first-party blog post, explains how developers can build meeting transcription products using its Scribe v2 batch model and Scribe v2 Realtime model through its API. The guide divides use cases by timing: real-time transcription for live captions and in-meeting bots, and batch transcription for post-meeting notes and records. According to the post, Scribe v2 Realtime reports 150 ms latency and supports up to 50 key terms for prompting. These are ElevenLabs' own product claims and have not been independently verified.
AIWritten by AI from the articles below · overview updated Oct 8, 7:54 PM ET
Check the sources:
Article timeline
Follow the coverage from different perspectives. Times are ET.
- ElevenLabs BlogHow to build a meeting transcription API with Scribe v2 and Scribe v2 Realtime
ElevenLabs explains how to build meeting transcription products using its Scribe v2 and Scribe v2 Realtime models through its API. Real-time transcription suits live captions and in-meeting bots, while batch transcription suits post-meeting notes and records, with Scribe v2 Realtime reporting 150 ms latency and supporting up to 50 key terms for prompting.
Heat trend
Not enough continuous observations to show a trend yet.