ᡤᡝᠯᡳ ᡩᡝ ᠵᡠᠸᡝᠨ

DiffRhythm: Lyrics to Song

ᠵᡠᠸᡝᠪᡠᠮᠪᡳ

ᠮᠣᡩᡝᠯ id diffrhythm
# 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/diffrhythm?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "lyrics": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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: $0.10 100 API ᠺᠷᡝᡩᡳᠲ ᡝᡵᡝ ᠵᠠᠯᡳᠨᡩᡝ ᠠᠰᡠᠮᠪᡳ

API ᡩᠠᠮᡠᠨ ᡤᠠᠯᠠ
Open model ᡥᡡᠯᠠᠨ ᡩᡝ ᡤᡳᠰᡠᠨ ᡤᡠᠯᡥᡠᠨ ᡩᠠᠯᡳᠨ ᡳ ᠠᠯᡳᠨ95–285 ᠰ #music

ᠰᡳᠯᡤᡳ ᡤᡳᠰᡠᠨ ᠪᡝ ᡝᠮᡠ ᡩᡠᠮᡝ ᡤᡳᠰᡠᠨ ᠪᡠᠶᠠᠮᠪᡳ, ᠮᠠᡵᠠᡥᠠ ᡳ ᡥᡡᠯᠠᠨ, ᠵᡠᠯᡝᠨ ᡤᡳᠰᡠᠨ ᠵᡠᠯᡝᠨ 95 s ᡠᠨᡩᡝ 285 s ᠵᠠᠯᡠᠨ

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

•ᡴᠠᠷᠠᡴᡡ

[chorus] ᠶᠠᠯᡠ [verse] ᠵᡝ ᡩᡠᠯᡝ ᠵᠣᠯᡤᠣᠨ ᠪᡳᠮᡝ ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳᠨ ᡳ ᡥᡡᠯᠠᠨ᠉

music_duration 95 s

ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳᠨ ᡳ ᡤᠠᠯᠠᠨ᠉

ᠵᡠᠯᡤᡝ ᠵᡝᡵᡤᡳ style_prompt · reference_audio_url · scheduler · cfg_strength · num_inference_steps

ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳᠨ ᡳ ᡶᠠᠯᡤᠠ ᡳ ᡥᡡᠯᠠᠨ᠉

ᠪᡠᠮᠪᡳ ᡝᠮᡠ ᡩᠠᡵᠠᠮᡝ

ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡳ ᠵᡠᠯᡝ ᡤᡳᠰᡠᠨ ᡳ URL᠉

scheduler ᠵᡠᠯᡝ euler

ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡩᡝ ᠵᡠᠯᡝ ᠰᠠᠮᡝᡥᠠ᠉

ᠵᡠᠯᡝ 4

ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡩᡝ ᠵᠠᠯᠠᠮᡝ CFG ᠵᠠᠯᠠᠨ᠉

ᠵᡠᠯᡝ 32

ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡳ ᠢᠯᠭᠠᠯᠠᠮᡝ ᠠᠵᠠᠯᠠᠨ ᡳ ᠵᠠᠯᠠᠨ᠉

POST /run/diffrhythm?wait=20 ᠵᠠᠯᡳᠨ → $0.10
# 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/diffrhythm?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "lyrics": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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

DiffRhythm: Lyrics to Song ᡠᡵᡝᠮᡝ

ᠰᡳᠯᡤᡳ ᡤᡳᠰᡠᠨ ᡩᡝᠵᡳᠨ ᡝᠮᡠ ᡩᡠᠮᡝ ᡤᡳᠰᡠᠨ ᠪᡠᠶᠠᠮᠪᡳ. `lyrics` ᡩᡝ ᠵᡝᠨᡝ ᠵᡠᠯᡝ ᠵᠠᠯᡠ ᠪᡳᠮᠪᡳ, ᡝᠮᡠ ᠵᡠᠯᡝ [verse] ᠠᠮᠪᡠᡵᡝ ᠵᡠᠯᡝ [chorus] ᡳ ᠵᠠᠯᡠ ᠪᡳ. `style_prompt` ᡠᠨᡩᡝ `reference_audio_url` ᡳ ᠪᡝ ᠠᠮᠪᡠᠯᠠᠮᡝ ᡤᡳᠰᡠᠨ ᡳ ᠵᠠᠰᠠᠮᡝ, `music_duration` 95s ᡠᠨᡩᡝ 285s ᠪᡝ ᠰᠣᠩᡤᠣᠯᠣᠮᡝ ᠵᠠᠰᠠᠮᠪᡳ. ᠪᡠᠶᠠᠮᡝ ᡳ ᠵᠠᠰᠠᠨ ᠪᡝ `scheduler`, `cfg_strength` (1 ᡩᡝ 10) ᡠᠨᡩᡝ `num_inference_steps` (10 ᡩᡝ 100) ᠪᡝ ᠠᡵᠠᠮᡝ ᠵᠠᠰᠠᠮᠪᡳ.

ᠵᠠᡴᡠᠨ

ᠵᡝᡵᡤᡳᡠᠯᠠᠮᡝ ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝᠠᠪᠠᠮᡝ ᠵᠠᠪᡠᠨ ᠵᠠᠯᠠᠨᡳ ᡤᡳᠰᡠᠨ
lyricsᡴᠠᠷᠠᡴᡡ
ᡠᠯᠠᠮᡝstring
[chorus] ᠶᠠᠯᡠ [verse] ᠵᡝ ᡩᡠᠯᡝ ᠵᠣᠯᡤᠣᠨ ᠪᡳᠮᡝ ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳᠨ ᡳ ᡥᡡᠯᠠᠨ᠉
reference_audio_urlᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝurl · audio
ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡳ ᠵᡠᠯᡝ ᡤᡳᠰᡠᠨ ᡳ URL᠉
style_promptᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝstring
ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳᠨ ᡳ ᡶᠠᠯᡤᠠ ᡳ ᡥᡡᠯᠠᠨ᠉
music_durationᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝenum
ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ95s
95s285s
ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳᠨ ᡳ ᡤᠠᠯᠠᠨ᠉
cfg_strengthᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝnumber
ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ4
1 – 10
ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡩᡝ ᠵᠠᠯᠠᠮᡝ CFG ᠵᠠᠯᠠᠨ᠉
schedulerᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝenum
ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝeuler
eulermidpointrk4implicit_adams
ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡩᡝ ᠵᡠᠯᡝ ᠰᠠᠮᡝᡥᠠ᠉
num_inference_stepsᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝinteger
ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ32
10 – 100
ᠮᡠᠰᡝᡳᠨ ᠪᡠᠶᡝᠮᡝ ᡳ ᠢᠯᠭᠠᠯᠠᠮᡝ ᠠᠵᠠᠯᠠᠨ ᡳ ᠵᠠᠯᠠᠨ᠉
ᡴᠠᠷᠠᡴᡡ

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": "diffrhythm",
  "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": 100,
    "usd": "0.10",
    "charged": 100,
    "refunded": 0
  },
  "input": {
    "lyrics": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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
    }
  },
  "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 ᠮᡠᠰᡝᡳᠨ ᡳ ᡶᡳᠯᡝ᠉

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