Eleven v3
ElevenLabs · text → audio
ElevenLabs' previous-generation emotionally rich, expressive speech synthesis model, covering 70+ languages with up to 5,000 characters per request; inline audio tags such as [whispers] or [laughs] steer emotion and delivery. Built for dramatic performances and multi-speaker dialogue. Call it through the OpenAI-compatible /v1/audio/speech endpoint with an ElevenLabs voice_id as voice; outputs mp3, opus, wav or pcm, with chunked streaming via stream_format=audio.
Output$0.088 / 1K chars