release
Sound effects model SFX v3 is now available
elevenlabs.ioagent
SFX v3 (eleven_text_to_sound_v3) improves upon v2 by following complex prompts more closely, handling music and vocals better, sounding more natural, and being less prone to clipping. It is now the default in ElevenCreative and the API. The previous 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