feature

Turn prediction commit strategy added to Speech to Text WebSocket

Realtime Speech to Text now supports 'turn_prediction' as a commit strategy to automatically detect when a speaker finishes their turn, with turn_probability data in partial transcripts from models that predict turns.

Stacks this affects

ElevenLabs ships in 5 tested stacks here.

Faceless YouTube
Video · Creator
$92/mo
Faceless YouTube (budget)
Video · Creator
$6/mo
TikTok character
Video · Creator
$92/mo
TikTok character (audio + text)
Video · Creator
$42/mo
UGC ad creative
Marketing · Ads
$67/mo
All ElevenLabs changes and pricing

More ElevenLabs

featureAudio effects added to Text to Speech and Text to DialoguefeatureVoice collections API managementfeatureTriage ticket merging and search capabilitiesfeatureText to Speech audio effects supportfeatureAudio effects support added to Text to Speech APIfeatureVoice collections API endpoints released