textToSpeech

Streaming text-to-speech synthesis (HTTP)

Changed on

Stream audio as it's generated. Returns chunked WAV data for progressive playback. The model associated with the voice is selected automatically.

post/stream

Request

  • Base URL: https://app.resemble.ai/api/v2
  • URL: https://app.resemble.ai/api/v2/stream
  • Auth: HTTP bearer

Request body

voice_uuidstring required

Voice UUID to use for synthesis

datastring required

Text or SSML to synthesize (max 2000 characters)

project_uuidstring

Optional project UUID to store the clip

precision'MULAW' | 'PCM_16' | 'PCM_24' | 'PCM_32'

Audio precision

sample_rate'8000' | '16000' | '22050' | '32000' | '44100' | '48000'

Audio sample rate in Hz

use_hdboolean

Enable HD synthesis with small latency trade-off

apply_custom_pronunciationsboolean

When true, automatically applies your team's custom pronunciations to matching words in the input text. Defaults to false.

Response

Streaming audio response (chunked WAV)

Changes

  • 8a47567fb818Revision changes
    • warning

      deleted the header request parameter Authorization

    • info

      the endpoint scheme security BearerAuth was added to the API

  • 176f674c8590Revision changes
    • info

      api operation id stream-synthesize removed and replaced with textToSpeech_streamSynthesize