Eleven v4 Turbo
ElevenLabs · text → audio
ElevenLabs' most emotive real-time speech synthesis model, with ~100ms median latency across 90+ languages at half the price of Eleven v4. Built for support agents, AI assistants and interactive characters. 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$0.044 / 1K chars