ElevenLabs

ElevenLabs Speech to Text Scribe's main functionality is to convert speech into text across multiple contexts and languages. It does this with high accuracy and offers two primary models: Scribe v2 for transcribing audio and video content, and Scribe v2 Realtime for immediate transcription of live applications.

Scribe v2 focuses on transcribing audio and video content into text. It is ideal for creating captions, subtitles, editable transcripts, labeling speakers, and marking sound events in transcripts. On the other hand, Scribe v2 Realtime is designed for real-time applications like live calls, meetings, or AI agents requiring immediate transcription. It employs a streaming-first architecture for instantaneous results.

The Scribe models offer exceptional transcription accuracy. Scribe v2 has been benchmarked as achieving industry-leading precision, outperforming other models in challenging audio conditions and across diverse accents. Scribe v2 Realtime delivers real-time results with the same high level of accuracy.

Scribe features speaker distinguishing functionality that allows it to accurately identify and label every speaker in a dialogue. This feature works even in situations where there are multiple overlapping speakers, making Scribe highly suited for group conversations and discussions.

ElevenLabs Speech to Text Scribe supports over 90 languages. These include but are not limited to: English, German, French, Japanese, Russian, Korean, Chinese, and more. This makes it a highly versatile tool for applications requiring multilingual transcription.