ElevenLabs Models
ElevenLabs Eleven v3, Eleven v4 and Eleven v4 Turbo via API: text-to-speech with inline audio tags, 90+ languages in v4 and a low-latency Turbo variant.
ElevenLabs, an AI audio company, develops the Eleven v3, Eleven v4 and Eleven v4 Turbo text-to-speech models. The company was founded in 2022 by Piotr Dąbkowski and Mati Staniszewski, who grew up in Poland, and has offices in London, New York and Warsaw.
Available models
2 model groups found
Eleven v4
elevenlabs/eleven-v4Text to Speech$0.08 / 1K characters
elevenlabs/eleven-v4-turboText to Speech$0.04 / 1K characters
1 capability
elevenlabs/eleven-v3Text to Speech$0.10 / 1K characters
About
ElevenLabs builds text-to-speech models that turn written text into expressive speech in many languages. Its platform also offers voice cloning, speech-to-text, dubbing and conversational voice agents.
- Eleven: Text-to-speech in Eleven v3, Eleven v4 and Eleven v4 Turbo; all take inline audio tags, v4 covers 90+ languages, and v4 Turbo is the low-latency variant.
Build with the API
One MuseSpan API key calls every ElevenLabs model on this page: copy a model ID and send it as the model field of your request.