Streaming text-to-speech synthesis (HTTP) | Resemble

Stream audio as it's generated. Returns chunked WAV data for progressive playback. 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 2000 characters)

project_uuidstringOptional

Optional project UUID to store the clip

precisionenumOptionalDefaults to PCM_32

Audio precision

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.

Streaming audio response (chunked WAV)

400

Bad Request Error

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