ᡤᡝᠯᡳ ᡩᡝ ᠵᡠᠸᡝᠨ

ThinkSound · Audio

ᠵᡠᠸᡝᠪᡠᠮᠪᡳ

ᠮᠣᡩᡝᠯ id thinksound/audio
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/thinksound/audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

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

ᡴᡳᠴᡝ ᡩᡝ ᠵᡠᠯᡤᡝ ᡤᡡᠨᠠᠨ ᠪᡝ $1.80 ᠪᠠᠶᠠᠮᠪᡳ ᠵᠣᡵᡤᠣᠨᡳ ᡠᠰᡳᡥᠠᡩᡝ, ᠰᡠᠯᡝ ᠠᠮᡝᠪᡠᠮᠪᡳ ᡝᡵᡝ ᠵᠠᠯᡳᠨᡩᡝ ᠠᠰᡠᠮᠪᡳ

API ᡩᠠᠮᡠᠨ ᡤᠠᠯᠠ
Open model ᠰᡠᠨᡤᠠ ᡩᡝ ᡤᡳᠰᡠᠨ #audio-generation#video-to-audio

ᠵᠠᠯᡳᠨ ᡩᡝᠯᡝᠨ ᡳ ᠠᡠᠳᡳᠣ ᡤᡝᠨᡝᠮᡝ᠂ ᠠᡠᠳᡳᠣ ᡳ ᠵᠠᠯᡳᠨ ᠪᠠᠨᠵᡳᠨᠠᠮᡝ ᠪᡳᠮᠪᡳ

Open model · ᡤᡳᠰᡠᠨ

ᡳᠨᡝ ᡝᠮᡠᠨᡳᠩᡤᡝ ᡝᡵᡝᠮᡝ ᡩᡝ

ᡝᡵᡝ ᠵᡠᠯᡝᠨ ᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠪᠠᠶᠠᠨᠠᠮᡝ ᠠᠮᡪᠠᠯᠠ ᡶᡳᠯᡝᠮᡝ ᠪᡝᠶᡝᠮᡝ᠃ API ᠵᡳᡵᡤᠠᡳ ᡤᠠᡳᡥᠠᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠵᠠᠯᠠᠨᠠᠮᡝ ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳ ᠰᡠᠯᡠᠨᡩᡝ ᠪᠠᠶᠠᠨᠠᠮᡝ᠂ ᠝ᠮᡤᡳ ᠮᡠᠰᡝ ᠠᠶᠠᠨ 7 ᡥᠠᠨ ᠰᠠᡳᠨᠠᠮᡝ᠃

ᡤᡳᠰᡠᠨ ᠪᡠᠶᡝᠮᡝ

ᠵᠠᡴᡠᠨᡳ ᠵᡠᠯᡝ ᡩᡝᡵᡤᡳ ᡩᡝᠪᡝᠰᡠᠮᡝ ᠵᡠᠯᡤᡝ ᠪᡠᠶᡝᠮᡝ᠈ ᡳᠨᡳ ᡤᡳᠰᡠᠨ ᠪᠠᡳ ᡝᠨᡝᠩᡤᡳ ᠠᠮᠪᡳ

ᠵᡠᠯᡝ

ᠪᡠᠶᡝᠮᡝᠨᡳ ᡤᡳᠰᡠᠨᡳ ᠵᠠᠯᠠᠨ; ᡥᡡᠯᠠᠨᡳ ᡩᡝᡵᡳ ᡥᡡᠯᠠᠨ ᠪᡝ ᠰᠣᠯᡥᡝᠮᡝ

•ᡴᠠᠷᠠᡴᡡ video_url
ᠪᡠᠮᠪᡳ ᡝᠮᡠ ᡩᠠᡵᠠᠮᡝ

ᠰᡠᠨᡤᠠ ᡳ URL, ᡤᡳᠰᡠᠨ ᡳ ᠪᡠᠶᡝᠮᡝ ᡩᡝ ᡠᠰᡳᡥᠠᠮᠪᡳ᠉

ᠵᡠᠯᡤᡝ ᠵᡝᡵᡤᡳ num_inference_steps · cfg_scale · seed
ᠵᡠᠯᡝ 24

ᡤᡳᠰᡠᠨ ᠪᡝ ᠪᡠᠶᡝᠮᡝᠨᡳ ᡩᡝᠯᡳᠮᡝᠨᡳ ᠵᠠᠯᠠᠨ

ᠵᡠᠯᡝ 5

ᡤᡳᠰᡠᠨ ᠪᡝ ᠪᡠᠶᡝᠮᡝᠨᡳ ᡩᠠᠯᡤᠠᠨᡳ ᠵᠠᠯᠠᠨ

ᠠᠮᠠᠰᡳ ᡩᠠᠮᡠ ᡳ ᠮᡝᡳᠰᡝᠨ ᡩᡝ ᡠᠰᡳᡥᠠᠮᠪᡳ᠉

POST /run/thinksound/audio?wait=20 ᠵᠠᠯᡳᠨ → $1.80
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/thinksound/audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

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

ᡝᠨᡳ ᠵᠠᠯᡳᠨ ᠪᡝ ᠵᠠᠯᠠᠨᠠᠮᡝ

ᡳᠨᡝ ᠵᠠᠯᠠᠨ ᡝᡵᡝ ᠪᡠᡵᡝᠪᡝᡵᡳ ᡩᡝ ᠪᡳᠮᡝ᠈ Doitong API ᡩᡝ ᠵᡝᠯᡤᡳ ᡩᠠᡵᠠᠮᡝ᠈ Remember ᠵᡠᠯᡝᠮᡝ ᡤᡳᠯᠠᠮᡝ localStorage ᡩᡝ ᠰᡠᠯᡝᠮᡝ ᠪᡳᠮᡝ API ᠵᠠᠯᠠᠨ ᠠᠪᠠᠮᡝ

ThinkSound · Audio ᡠᡵᡝᠮᡝ

`video_url` ᡳ ᠵᠠᠯᡳᠨ ᡩᡝ ᠠᡠᠳᡳᠣ ᠪᡝ ᠪᠠᠨᠵᡳᠨᠠᠮᡝ ᠵᠠᠯᡳᠨ ᡩᡝ ᡝᠮᡠᠯᡝ ᠠᡠᠳᡳᠣ ᠪᡝ ᡤᡝᠨᡝᠮᡝ ᠪᡳᠮᠪᡳ᠉ ᠰᡠᠯᡝᡵᡝ ᠠᡠᠳᡳᠣ ᠪᡝ ᡩᠠᠯᡳᠨ ᡩᡝ ᠮᡠᠶᠠᠩᡤᠠᠮᡝ ᠠᡳᠰᡳ ᠵᠠᠰᠠᠮᡝ ᠵᠠᠯᡳᠨᠠᠮᡝ᠉ ᠠᠴᠠᠨ `prompt` ᡳ ᠵᠠᠰᠠᠮᡝ᠂ ᠠᡳᠰᡳ ᠵᠠᠯᡳᠨ ᡳ ᠠᠴᠠᠨ ᡳ ᠠᠪᠠᠮᡝ ᠪᡳᠮᠪᡳ᠉ `seed`᠂ `num_inference_steps` (2 ᡩᡝ 100) ᠠᡳᠰᡳ `cfg_scale` (1 ᡩᡝ 20) ᠪᡝ ᠵᠠᠪᡠᠮᡝ ᠪᡳᠮᠪᡳ᠉

ᠵᠠᡴᡠᠨ

ᠵᠠᡴᡠᠨᡳ ᡤᡳᠰᡠᠨ ᠵᡝᠯᡤᡳ ᠠᠪᠠᠮᠪᡳ᠈ ᠨᡝᠮᡝ ᠮᡠᠰᡝ ᡠᠯᠠᠮᠪᡳ ᠵᠠᡴᡠᠨᡳ ᡤᡳᠰᡠᠨ

ᠵᡝᡵᡤᡳᡠᠯᠠᠮᡝ ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝᠠᠪᠠᠮᡝ ᠵᠠᠪᡠᠨ ᠵᠠᠯᠠᠨᡳ ᡤᡳᠰᡠᠨ
video_urlᡴᠠᠷᠠᡴᡡ video
ᡠᠯᠠᠮᡝurl · video
ᠰᡠᠨᡤᠠ ᡳ URL, ᡤᡳᠰᡠᠨ ᡳ ᠪᡠᠶᡝᠮᡝ ᡩᡝ ᡠᠰᡳᡥᠠᠮᠪᡳ᠉
promptᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝstring
ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ
ᠪᡠᠶᡝᠮᡝᠨᡳ ᡤᡳᠰᡠᠨᡳ ᠵᠠᠯᠠᠨ; ᡥᡡᠯᠠᠨᡳ ᡩᡝᡵᡳ ᡥᡡᠯᠠᠨ ᠪᡝ ᠰᠣᠯᡥᡝᠮᡝ
seedᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝinteger | null
ᠠᠮᠠᠰᡳ ᡩᠠᠮᡠ ᡳ ᠮᡝᡳᠰᡝᠨ ᡩᡝ ᡠᠰᡳᡥᠠᠮᠪᡳ᠉
num_inference_stepsᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝinteger
ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ24
2 – 100
ᡤᡳᠰᡠᠨ ᠪᡝ ᠪᡠᠶᡝᠮᡝᠨᡳ ᡩᡝᠯᡳᠮᡝᠨᡳ ᠵᠠᠯᠠᠨ
cfg_scaleᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝnumber
ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ5
1 – 20
ᡤᡳᠰᡠᠨ ᠪᡝ ᠪᡠᠶᡝᠮᡝᠨᡳ ᡩᠠᠯᡤᠠᠨᡳ ᠵᠠᠯᠠᠨ
ᡴᠠᠷᠠᡴᡡ ᠵᠠᡴᡠᠨᡳ ᡤᡳᠰᡠᠨ᠈ ᠮᡠᠰᡝ ᡝᠮᡠ ᠠᠪᠠᠮᠪᡳ

ᠪᡠᠮᠪᡳᠯᡝᠰᡝ ᡝᠮᡠ ᡤᡝᠮᡠᠨᡳ https:// URL᠈ 10 MB ᡩᡝ ᡩᡝᠷᡤᡳ data: URI ᠵᡝᡵᡤᡳ ᡝᠮᡝ᠈ ᡳᠨᡝ ᠪᡠᠮᠪᡳᠯᡝᠰᡝᠨᡳ file_url ᠠᠪᠠᠮᠪᡳ ᠪᡠᠮᠪᡳ

ᠪᡠᠶᡝᠮᡝ

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "thinksound/audio",
  "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": 1800,
    "usd": "1.80",
    "charged": 1800,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "prompt": "An acoustic guitar being played indoors."
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
ᡤᡝᠯᡝᠮᡝ ᡥᡡᠯᡤᡠᠨᡳ ᡳᠨᡠᡝᠯᡝᡥᡝ outputs[].url ᠰᡠᠯᡠᠨ ᡩᡝ ᠰᡳᡵᡝ ᡶᡳᠯᡝ᠈ ᠝ᠮᡤᡳ ᠮᡠᠰᡝ ᠠᠪᠠᠯᡳ ᠵᡝᠮᡤᡳᠨ GB-ᠪᡳᠶᠠ ᠵᡝᠮᡤᡳᠨ ᠪᡝ ᡝᠮᡠᠯᡝᠮᡝ ᠠᠪᠠᠯᡳ 7 ᡥᠠᠨ ᠰᡳᠯᡤᠠᠨ ᡩᡝ᠈ ᠰᡳᠨᡳ ᠪᠠᠯᠠᠨᠰᡳ ᠵᡠᠶᡝᡵᡝᠨ ᠠᠪᠠᠯᡳ ?storage= ᡩᡝ ᡝᠵᡝᠨ ᡥᠠᠯᠠᠮᡝ᠉
ᡝᠮᡠ ᡤᡳᠰᡠᠨ ᡝᠮᡠ ᠮᠣᡩᡝᠯ ᡩᡝtype, url, content_type, width, height ᠮᠠᠩᡤᡳ duration᠈ ᠵᠠᠯᠠᠨ᠈ ᠪᡠᠵᡠᠮᠪᡳ ᠮᠠᠩᡤᡳ ᠵᡝᡵᡤᡳ ᡩᡝᠨᡳ᠈ output ᠮᠣᡩᡝᠯᡳᠨᡳ ᡝᠮᡠ ᠵᠠᠯᠠᠨ
ᠪᡠᠶᡝᠮᡝᠨᡳ ᡤᡳᠰᡠᠨ
audio
object {url, content_type, file_name, file_size}ᠪᡠᠶᡝᠮᡝ ᠵᡠᡴᡴᠠᠨ ᡤᡳᠰᡠᠨ ᡳ ᡶᡳᠯᡝ᠉
prompt
stringᡤᡳᠰᡠᠨ ᠪᡝ ᠪᡠᠶᡝᠮᡝ ᠵᠠᠯᠠᡥᠠ ᡥᡡᠯᠠᠨ

ᡝᠯᡤᡳ ᡩᠠᠯᡳᠨ: ᠰᡠᠨᡤᠠ ᡩᡝ ᡤᡳᠰᡠᠨ

AI ᠠᡤᡝᠨᡨᡳ ᡠᠴᡠᠷᡳ᠈ ᡝᡵᡝ ᡩᡝᠪᡝᡵᡳ Markdown ᠰᡳᠨᡩᠠᡵᡳ https://doitong.com/mnc/developers/models/thinksound/audio.md. ᡝᡵᡝ ᠮᠣᡩᡝᠯ ᠵᠠᡴᡠᠨ ᠰᡠᠯᡠᠮᡝ https://doitong.com/developers/llms.txt