Skip to content

Qwen 3 TTS - Clone Voice [1.7B]

Integrate

Model id qwen-3-tts/clone-voice/1.7b
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/qwen-3-tts/clone-voice/1.7b?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Files like the example: $0.001 1 API credit · ≈ ₽0.11 your files are measured before the run Run it on this page

Get API key
Alibaba Audio Reference inputs #clone-voice#voice-clone

Builds a reusable speaker embedding from a reference clip, larger 1.7B variant of the voice cloner

Alibaba · Data (JSON)

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required audio_url
Drop a file, or

Voice-cloning audio URL; a brief, clean speech recording is sufficient as the reference, provided its duration does not exceed 300 seconds (5 minutes).

Advanced reference_text · enable_safety_checker

Reference text, optionally supplied to improve synthesis with a cloned voice, must be the text used to create the speaker embedding.

POST /run/qwen-3-tts/clone-voice/1.7b?wait=20 quote → $0.001
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/qwen-3-tts/clone-voice/1.7b?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Qwen 3 TTS - Clone Voice [1.7B]

Creates a speaker embedding in safetensors format from a reference recording given as `audio_url`, which can be at most 300 seconds long. Use the result with the text-to-speech endpoint to speak in the cloned voice. `reference_text` is optional and may help quality. This is the 1.7B sized counterpart of the 0.6B cloner.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
audio_urlrequired audio
Typeurl · audio
Voice-cloning audio URL; a brief, clean speech recording is sufficient as the reference, provided its duration does not exceed 300 seconds (5 minutes).
reference_textoptional
Typestring | null
Reference text, optionally supplied to improve synthesis with a cloned voice, must be the text used to create the speaker embedding.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Screening can be relaxed by setting false, provided the caller is authorized.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "qwen-3-tts/clone-voice/1.7b",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1,
    "usd": "0.001",
    "charged": 1,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "speaker_embedding": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
speaker_embedding
object {url, content_type, file_name, file_size}Speaker embedding generated as a safetensors file.

More models: Audio

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/qwen-3-tts/clone-voice/1.7b.md. All models and guides: https://doitong.com/developers/llms.txt