release
SFX v3 sound effects model released with improved prompt following and natural audio quality
elevenlabs.ioagent
The new eleven_text_to_sound_v3 model is now available to all workspaces. It follows multi-instruction prompts more closely, handles music and vocals better, and reduces clipping on high-frequency sounds compared to v2. The older eleven_text_to_sound_v2 model is deprecated and will be removed on March 1, 2027.
Stacks this affects
ElevenLabs ships in 5 tested stacks here.
More ElevenLabs
releaseSFX v3 sound effects model releasedfeatureProfessional Voice Clone fine-tuning available for Eleven v4featureRealtime entity redaction added to Speech to TextshutdownSound effects model v2 deprecated with March 1, 2027 removalshutdownMusic model v1 deprecated with January 31, 2027 removalshutdownCritical model deprecations: OpenAI gpt-5 family (Dec 11), Claude Sonnet 4.5 (Nov 30), and ElevenLabs audio models