Eleven Multilingual v2
ElevenLabs · text → audio
Lifelike, consistent-quality multilingual speech synthesis covering 29 languages with up to 10,000 characters per request; the most stable on long-form generation. Built for character voiceovers and professional or e-learning content. 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