Synchronous text-to-speech synthesis | Resemble

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

AuthorizationBearer

This endpoint expects an object.

voice_uuidstringRequired

Voice UUID to use for synthesis

datastringRequired

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

project_uuidstringOptional

Optional project UUID to store the clip

titlestringOptional

Optional title for the generated clip

precisionenumOptionalDefaults to PCM_32

Audio precision for WAV output

Allowed values:

output_formatenumOptionalDefaults to wav

Audio output format

Allowed values:

sample_rateenumOptional

Audio sample rate in Hz

use_hdbooleanOptionalDefaults to false

Enable HD synthesis with small latency trade-off

apply_custom_pronunciationsbooleanOptionalDefaults to false

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

Successful synthesis

successbooleanOptional

audio_contentstringOptionalformat: "byte"

Base64-encoded audio bytes

audio_timestampsobjectOptional

durationdoubleOptional

Audio duration in seconds

synth_durationdoubleOptional

Raw synthesis time

output_formatstringOptional

sample_rateintegerOptional

titlestringOptional

issueslist of stringsOptional

400

Bad Request Error

401

Unauthorized Error

$	curl -X POST https://f.cluster.resemble.ai/synthesize \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"voice_uuid": "55592656",
>	"data": "Hello from Resemble!"
>	}'