Meet Scribe

This video introduces ElevenLabs Scribe, an advanced AI transcription model that outperforms competitors in accuracy and features. It highlights multilingual support, character-level timestamps, HIPAA compliance, and multi-speaker diarization, showcasing its versatility across various applications.

Introducing Scribe — the most accurate Speech to Text model. Try ElevenLabs: https://elevenlabs.io?utm_source=youtube&utm_medium=organic&utm_campaign=not_set&utm_content=meet_scribe It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing. It achieves the highest accuracy for the most common languages. And it significantly improves the performance of previously underserved languages such as Serbian, Cantonese, and Gujarati. We have a low-latency version of Scribe coming soon, extending Scribe to real-time use cases. Scribe is available today in both our UI and API. It’s priced at $0.40 per hour of input audio, with an additional 50% discount available for the next 6 weeks. Join us next week for a virtual event with the team behind the launch: https://app.livestorm.co/elevenlabs/meet-scribe-the-worlds-most-accurate-transcription-model Try ElevenLabs: https://elevenlabs.io?utm_source=youtube&utm_medium=organic&utm_campaign=not_set&utm_content=meet_scribe MB01ZJTXVYQWMNX