API Reference
Create a Kling custom voice
Create a site voice for kling-4.0 using a local PCM WAV upload or public media URL.
Preview guide
Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.
Updated · Reviewed
Endpoint and authentication
POST https://api.tu-zi.com/v1/general/custom-voices
Transport: json
Use an inference API key. Examples contain placeholders; read credentials from environment variables.
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
Before calling
- Examples use this site's address. For another gateway, replace only the site address and keep the full endpoint path.
- Use an inference key created on this site's token page. Set the
API_KEYenvironment variable or replaceYOUR_API_KEY, as shown in the selected example.
Constraints
Local WAV upload
Alternatively send multipart/form-data with voice_name and file: a 5–30 second PCM WAV, at most 15 MiB. Let the HTTP client set the multipart boundary; do not include voice_url.
curl --fail-with-body "$TUZI_BASE_URL/v1/general/custom-voices" \
-H "Authorization: Bearer $TUZI_API_KEY" \
-F "voice_name=My voice" \
-F "file=@./sample.wav;type=audio/wav"
Set TUZI_BASE_URL to this site API origin and TUZI_API_KEY to its inference credential. No model field is needed. A model-restricted key must allow kling-custom-voice, and kling-4.0 for video generation. Listing, deletion, callbacks and video_id extraction are not exposed.
Minimal request example
{
"voice_name": "My voice",
"voice_url": "https://example.com/sample.wav"
}
Confirming success
Check HTTP status, the business status in the body and the required result fields. Do not rely only on HTTP 200 or the script exit code.
Follow the asynchronous workflow to a successful terminal state and verify readable output. A task ID, queued or processing is not completed generation.
Body parameters
| Field | Type | Required | Description / constraints |
|---|---|---|---|
| voice_name | string | Yes | Voice name, 1–20 characters. Example: My voice |
| voice_url | string | Yes | Required for JSON: public HTTP(S) MP3/WAV/MP4/MOV with 5–30 seconds of clear single-speaker speech. Example: https://example.com/sample.wav |
Response fields
| Field | Type | Description / constraints |
|---|---|---|
| data.task_id | string | Site task ID; save it for polling. |
| data.task_status | string | submitted only means accepted. |
Illustrative response; some endpoints show essential fields only. Optional fields may be absent.
{
"code": 0,
"message": "SUCCEED",
"data": {
"task_id": "task_example",
"task_status": "submitted"
}
}
Asynchronous workflow
Poll GET /v1/general/custom-voices/{task_id} with the same site API key. Wait on submitted/processing, read data.task_result.voices[0].voice_id on succeed, and stop on failed. Polling has no model generation charge; creation and video generation are charged separately. Save task_id and bound polling by a deadline. Check task logs after a lost creation response; do not automatically repeat POST.
Errors and retries
Check HTTP status and protocol-specific errors; do not mix error formats across protocols.
- 401/403: check credentials and permissions.
- 429: classify temporary throttling, exhausted quota, or service capacity failure; only transient failures merit bounded backoff.
- 5xx: inspect the gateway, upstream, and model/channel configuration.
Error bodies may contain error/message/code depending on the protocol.
- Use bounded exponential backoff for reads encountering transient errors; fix parameter, authentication, quota, or configuration failures first.
- Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.
兔子API