Get the transcription of a style's reference audio

Read the ASR transcription of this style's reference audio (data is the string itself, not an object).

Three lookup paths:

The style already has cached textAsr → return it directly;

v4.0 voice → take the transcription produced by emotion-controllable annotation, write it back as textAsr, and recompute base speech rate;

Otherwise → query style info and likewise write the cache on success.

Transcription may be null: when the query succeeds but produces no transcription, { "status": 200, "data": null } is returned; this is not an error.
Only the query itself failing returns 500 SYSTEM_INTERNAL_ERROR.

A missing style ID returns 404 RESOURCE_NOT_FOUND (note: not VOICE_NOT_FOUND).

You can only operate voices you created, and the voice must not be in creating / failed. See the "Create a voice character" document.

INFO

Deprecated alias: /api/tts/voice/{id}/prompt/{promptId}/stt. See the site document "Versions and migration".

INFO

See the Errors document for the full code reference. Always use the X-Vocu-App-Request-Id response header when troubleshooting.

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Responses

🟢200Success

application/json

Retrieved. data is the transcript string, or null when there is no transcript.

Bodyapplication/json

Example

{
    "status": 200,
    "data": "The weather is nice today. A good day to go out."
}

🟠400Bad request

🟠401Unauthorized

🟠403Forbidden

🟠404Not found

🟠409Conflict

🟠429Rate limited

🔴500Server error

Get the transcription of a style's reference audio

Request

Request Code Samples

Responses