release
SFX v3 sound effects model now available with improved prompt adherence and audio quality
elevenlabs.ioagent
ElevenLabs released eleven_text_to_sound_v3, which better follows complex prompts, handles music/vocals more effectively, and generates more natural audio with less high-frequency clipping. The previous v2 model 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