Build production-ready audio AI in minutes

The ElevenLabs API provides programmatic access to our AI models for voice, music, sound effects, dubbing, and transcription. You can integrate these capabilities directly into your applications, workflows, and production pipelines.

Text to Speech (TTS): Turns text into lifelike audio with nuanced intonation, pacing, and emotional awareness. Speech to Text (Transcription): Turns spoken audio into text with state-of-the-art accuracy. Music: Generate music from text. Studio: Manage ElevenLabs Studio projects via API. Text to Dialogue: Create natural-sounding dialogue from text. Voice Changer: Replace one voice with another. Voice Isolator (Audio Isolation): Isolate vocal tracks from background noise in audio. Dubbing: Dub audio and videos seamlessly (translate and voice-over content in other languages). Sound Effects: Create cinematic sound effects from text descriptions. Voice Design: Create custom AI voices from text prompts when a needed voice isn’t available in the library. Voice Remixing: Transform and enhance existing voices (remix voice characteristics or style). Forced Alignment: Align text to audio (get precise word-level timestamps for given audio and transcript). Pronunciation Dictionaries: Customize how specific words or phrases are pronounced by TTS models (upload lexicon files to control pronunciation). Audio Native: An embeddable audio player that automatically voices webpage content using ElevenLabs TTS service. Agents Platform (Voice Agents): Deploy intelligent voice agents for interactive applications. These endpoints support building, launching, and managing AI-driven voice agents (with components like conversations, knowledge bases, phone integration).

Common use cases include content localization pipelines, automated video production, conversational interfaces, accessibility tools, and training content generation. The API is designed for both real-time and batch processing.

All API requests require an API key passed in the xi-api-key header. Keys are generated in your account settings and can be scoped to specific workspaces.

Usage limits vary by plan and endpoint. PAYG usage is enabled from our Starter plan and above.

Yes. Official SDKs are available for Python & JavaScript/TypeScript, and additional platforms like Flutter, Swift, and Kotlin for our Agents platform.

Text to Speech is billed per character. Speech to Text is billed per audio minute. Music and Sound Effects are billed per generation. Dubbing is billed per source audio minute.

Yes. You can reference any voice in your library by ID, including professional voices, cloned voices, and voices you've designed.

Yes. Content generated through the API using ElevenLabs models is commercially licensed. Music requires an additional license for advertising, film, TV, games, and enterprise distribution.

Text to Speech typically responds in under 500ms for streaming. Speech to Text processes at 20-50x real-time depending on file size. Dubbing and Music are batch operations with processing times proportional to content length.

Yes. Text to Speech and Speech to Text both support streaming output, allowing you to use the APIs in real-time applications.

The API returns standard HTTP status codes. Rate limit errors return 429. Invalid requests return 400 with error details. Authentication failures return 401.

Complete API reference, code examples, and integration guides are available at elevenlabs.io/docs/api-reference

Yes. Enterprise plans include dedicated support, SLAs, custom rate limits, SSO, SOC 2 compliance, and MSAs.