Synthesize speech and play it on a leg
Synthesizes the provided text using the configured TTS provider and plays the audio on the leg. When TTS_CACHE_ENABLED=true, identical requests (same text, voice, model, language, and prompt) are stored on disk in TTS_CACHE_DIR and persist across restarts, without calling the external provider.
Request body
Response
TTS playback started
Changes
Changed in 5 of the 67 revisions of this API.46
- ▲
removed the enum value
azureof the request propertyproviderrequest-property-enum-value-removed
- ▲
- ○
added the new
azureenum value to the request propertyproviderrequest-property-enum-value-added
- ○
- ○
added the new
deepgramenum value to the request propertyproviderrequest-property-enum-value-added
This revision also has 1 change that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
- ○
- ▲
removed the enum value
deepgramof the request propertyproviderrequest-property-enum-value-removed
- ○
the request property
model_idbecame optionalrequest-property-became-optional
- ○
the request property
volumebecame optionalrequest-property-became-optional
- ○
added the required property
tts_idto the response with the200statusresponse-required-property-added
This revision also has 40 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
- ▲
- ▲
the request property
model_idbecame requiredrequest-property-became-required
- ▲
removed the required property
tts_idfrom the response with the200statusresponse-required-property-removed
- ○
the request property
volumewith a default value became requiredrequest-property-became-required-with-default
This revision also has 6 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
- ▲