v44

latestOpenAPI 3.1.0Proprietaryraw.githubusercontent.com2026-05-192301780.0 KB

Voice

Stream text-to-speech audio

Convert text to speech using ElevenLabs AI voices with streaming for real-time playback. Returns audio data as an MP3 stream for immediate playback with minimal latency. Perfect for legal document narration, client presentations, or accessibility features.

post/voice/v1/speak/stream

Request body

textstring required

Text to convert to speech

voice_idstring

ElevenLabs voice ID (defaults to Rachel for professional clarity)

model_id'eleven_monolingual_v1' | 'eleven_multilingual_v1' | 'eleven_multilingual_v2' | 'eleven_turbo_v2'

TTS model to use

language_codestring

Language code (e.g., 'en', 'es', 'fr')

output_format'mp3_44100_128' | 'mp3_22050_32' | 'pcm_16000' | 'pcm_22050' | 'pcm_24000' | 'pcm_44100'

Audio output format

optimize_streaming_latencyinteger

Optimize for streaming latency (0-4)

seedinteger

Random seed for reproducible generation

previous_textstring

Previous text for context

next_textstring

Next text for context

apply_text_normalizationboolean

Apply text normalization

enable_loggingboolean

Enable request logging

Response

Audio stream successfully generated