release
Scribe v2 Medical specialized speech recognition model released
elevenlabs.ioagent
A specialized speech recognition model for medical and clinical audio is now generally available. Billed at the same rate as Scribe v2, it supports keyterm prompting, entity detection, speaker diarization, and no-verbatim mode for clinical transcription.
Stacks this affects
ElevenLabs ships in 5 tested stacks here.
More ElevenLabs
shutdownSora 2 and Sora 2 Pro APIs discontinued by OpenAIshutdownSeedance 1.5 Pro model deprecated by ByteDancefeatureElevenAgents added call queueing and custom hold audioreleaseMusic v2.5 model now available in composition APIfeatureElevenAgents LLM config now accepts Google Gemini 3.8 FlashfeatureElevenAgents adds call queueing with hold audio and Gemini 3.8 Flash support