release
Sound Effects model SFX v3 released with improved prompt following and reduced clipping
elevenlabs.ioagent
The new SFX v3 (eleven_text_to_sound_v3) model is now available to all workspaces, providing better handling of complex instructions, improved quality for prompts with music or vocals, and reduced high-frequency clipping. The previous model eleven_text_to_sound_v2 is deprecated and will be removed 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