Young Tries AI

Everything on Scribe v3 Live

2 mentions, newest first.

  1. ElevenLabs Scribe v3 cuts word errors 27% against Scribe v2 across 102 languages

    ElevenLabs reports that Scribe v3 for recorded audio makes 27% fewer word errors than Scribe v2 across 102 languages and 17% fewer diarization errors on recordings with three or more speakers. Scribe v3 Live, the realtime model, makes 43% fewer errors than Scribe v2 Realtime and adds speaker diarization for the first time.

    Usable today
  2. ElevenLabs adds Scribe v3 and Scribe v3 Live to its Speech to Text API

    Scribe v3 (scribe_v3) transcribes recorded audio and Scribe v3 Live (scribe_v3_live) works in real time. ElevenLabs says Scribe v3 makes 27% fewer word errors than Scribe v2 on FLEURS across 102 languages. It adds numbers_format and secondary_language_codes for audio that mixes languages. Scribe v2 and Scribe v2 Realtime remain available.

    Usable today