v3

latestOpenAPI 3.1.02026-07-31112356215.0 KB

textToSpeech

Synchronous text-to-speech synthesis

Generate speech synchronously from text or SSML. Returns complete audio as base64. The model associated with the voice is selected automatically.

post/synthesize

Authorizationstring required

voice_uuidstring required

Voice UUID to use for synthesis

project_uuidstring

Optional project UUID to store the clip

titlestring

Optional title for the generated clip

datastring required

Text or SSML to synthesize (max 3,000 characters)

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

Audio precision for WAV output

output_format'wav' | 'mp3'

Audio output format

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.

Successful synthesis

successboolean

audio_contentstring byte

Base64-encoded audio bytes

durationnumber double

Audio duration in seconds

synth_durationnumber double

Raw synthesis time

output_formatstring

sample_rateinteger

titlestring

issuesstring[]