ElevenLabs' newest voice models are in Text-to-Speech: Eleven v4, its most expressive voice, at the same price per character as Eleven v3, and Eleven v4 Turbo, a faster voice that also acts out audio tags such as [laughs], at the same price as Flash v2.5. Eleven Music v2.5 joins for songs, at the same price per minute as Eleven Music v2. We listened to all three before adding them, and Auto can now choose them; the voices and the music model Auto prefers stay the same. ElevenLabs retires Eleven Music v1 on 31 January 2027, so a song set to Eleven Music v1 is now made with Eleven Music v2.5, at the same price per minute.