ElevenLabs Documentation
How ElevenLabs works
ElevenLabs provides AI voice infrastructure: text-to-speech, speech-to-text, voice cloning, conversational agents, and generative audio. All capabilities are accessible through a REST API with official Python and TypeScript SDKs, and through a web application for no-code use.
Voices are the speech persona used in audio generation. Each voice has a unique ID — for example, JBFqnCBsd6RMkjVDRZzb — that you pass in every API request. ElevenLabs maintains a library of 5,000+ voices. You can also clone a voice from an audio recording or generate one from a text description.
Models control the quality, latency, and language coverage of generated audio. eleven_v3 produces the most expressive output across 70+ languages. eleven_flash_v2_5 targets real-time use at ~75ms latency. Each capability — speech-to-text, music, sound effects — has its own dedicated model.
Credits are the unit of API consumption. Text-to-speech costs one credit per character of input text. Other operations are charged per second of audio processed. Credits reset monthly and unused credits roll over for up to two months. See pricing for a full breakdown.
Choose your path
Meet the models
Our most emotionally rich, expressive speech synthesis model
Lifelike, consistent quality speech synthesis model
Our fast, affordable speech synthesis model
State-of-the-art speech recognition model
Real-time speech recognition model
Browse by capability
Convert text into lifelike speech
Transcribe spoken audio into text
Generate music from text
Create natural-sounding dialogue from text
Generate images and videos from text
Modify and transform voices
Isolate voices from background noise
Dub audio and videos seamlessly
Create cinematic sound effects
Clone and design custom voices
Transform and enhance existing voices
Align text to audio
Deploy intelligent voice agents
