Correct the transcription of a style's reference audio

Manually correct the transcription of this style's reference audio. After write, base speech rate (baseSpeechRate) is recomputed from the new text and the audio duration.

v4.0 vs non-v4.0 behavior differs (routes/voice/prompt.js:101-126):

Non-v4.0: first push the new text to the upstream style record; push failure returns 500 SYSTEM_INTERNAL_ERROR and the local copy is not written;

v4.0: transcription is stored locally only, and the old transcription in the cached annotation is discarded, so the next generation re-derives it and does not keep using the text the user just corrected.

Two content-safety checks: first a standalone UGC check on text (non-strict tier), then a profile check on "style description + text" together.
The former failing returns SAFETY_CONTENT_REJECTED; the latter failing returns SAFETY_PROFILE_REJECTED; both response bodies include traceId.

Ownership and status checks (modules/routeHelpers.js:254-280, modules/voiceFactory.js:257-270):

Voice does not exist, does not belong to the current user, or has been soft-deleted → 404 VOICE_NOT_FOUND (the three cases are not distinguished)

status = creating → 409 VOICE_CREATING

status = failed → 400 VOICE_CREATE_FAILED

from != upload (e.g. a market-purchased / community-imported voice) → 403 AUTH_FORBIDDEN

Lazy version migration has not finished → 500 SYSTEM_INTERNAL_ERROR (retryable)

Legacy alias: /api/tts/voice/{id}/prompt/{promptId}/stt — still supported for backward compatibility; use the primary path for new integrations.

Error responses take the shape { status, code, message, requestId? }. code is always the parent code — sub codes only change message and never appear in the body. requestId is present only on reportable-tier errors, so use the X-Vocu-App-Request-Id response header when troubleshooting (it is written unconditionally on every response). See the "Errors" document for the full code reference.

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

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

Responses

🟢200成功

application/json

写入成功，返回更新后的完整语音角色对象

Bodyapplication/json

Example

{
    "status": 200,
    "data": {
        "id": "7c3d9a12-5e84-4b06-9f21-8ad3e6b40c57",
        "name": "温柔女声",
        "status": "pending",
        "from": "upload",
        "version": "v3.0",
        "originId": null,
        "userId": "2f81b40c-9d63-4e17-a5b8-31c7d0e926af",
        "avatar": "https://storage.vocu.ai/avatar/voice/2f81b40c-9d63-4e17-a5b8-31c7d0e926af/7c3d9a12-5e84-4b06-9f21-8ad3e6b40c57.png",
        "createdAt": "2026-07-14T06:22:08.000Z",
        "updatedAt": "2026-08-19T11:04:37.000Z",
        "deletedAt": null,
        "metadata": {
            "description": "偏日常叙述的温柔女声",
            "avatar": "https://storage.vocu.ai/avatar/voice/2f81b40c-9d63-4e17-a5b8-31c7d0e926af/7c3d9a12-5e84-4b06-9f21-8ad3e6b40c57.png",
            "prompts": [
                {
                    "id": "default",
                    "name": "默认",
                    "description": "平稳叙述",
                    "enhance": true,
                    "language": "zh",
                    "flags": [
                        "20250227-vcb",
                        "v3:20250828-vfa"
                    ],
                    "playBackAudio": "https://storage.vocu.ai/prompt/2f81b40c-9d63-4e17-a5b8-31c7d0e926af/default-playback.mp3",
                    "promptOriginAudioStorageUrl": "https://storage.vocu.ai/prompt/2f81b40c-9d63-4e17-a5b8-31c7d0e926af/default-origin.wav",
                    "baseSpeechRate": 4.6
                }
            ]
        }
    }
}

🟠400请求有误

🟠401没有权限

🟠403禁止访问

🟠404记录不存在

🟠409

🟠429

🔴500服务器错误

Correct the transcription of a style's reference audio

Request

Request Code Samples

Responses