Ruka hadi kwenye maudhui

DiffRhythm: Lyrics to Song

Unganisha

Kitambulisho cha modeli 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"

Ombi hili: $ 0.10 salio za API 100 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Open model Maandishi hadi Muziki Ingizo za marejeleo95–285 s #music

Hubadilisha maneno ya wimbo kuwa wimbo kamili, ikiwa na kidokezo cha mtindo, sauti ya marejeo na urefu wa hiari wa 95 s au 285 s

Open model · Sauti

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

•inahitajika

Kidokezo cha kutengeneza wimbo chenye sehemu mbili haswa, kila moja ikianzishwa na [chorus] au [verse].

music_duration 95 s

Urefu wa muziki utakaotengenezwa.

Ya kina style_prompt · reference_audio_url · scheduler · cfg_strength · num_inference_steps

Kidokezo kinachoeleza mtindo wa muziki unaotengenezwa.

Dondosha faili, au

URL inayoelekeza kwenye sauti ya marejeleo ya kutengeneza muziki.

scheduler chaguomsingi euler

Scheduler inayotumika wakati wa kutengeneza muziki.

chaguomsingi 4

Nguvu ya CFG inayotumika wakati wa kutengeneza muziki.

chaguomsingi 32

Idadi ya hatua za inference za kutengeneza muziki.

POST /run/diffrhythm?wait=20 makadirio → $ 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"

Endesha ombi hili

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Pata ufunguo wa API

Kuhusu DiffRhythm: Lyrics to Song

Huunda wimbo kamili kutoka mashairi. `lyrics` lazima iwe na angalau sehemu mbili, kila moja ikianza na lebo ya [verse] au [chorus]. Elekeza sauti kwa `style_prompt` au `reference_audio_url`, na uchague `music_duration` ya 95s au 285s. Vidhibiti vya sampuli vinajumuisha `scheduler`, `cfg_strength` (1 hadi 10) na `num_inference_steps` (10 hadi 100).

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo
lyricsinahitajika
Ainastring
Kidokezo cha kutengeneza wimbo chenye sehemu mbili haswa, kila moja ikianzishwa na [chorus] au [verse].
reference_audio_urlsi lazima
Ainaurl · audio
URL inayoelekeza kwenye sauti ya marejeleo ya kutengeneza muziki.
style_promptsi lazima
Ainastring
Kidokezo kinachoeleza mtindo wa muziki unaotengenezwa.
music_durationsi lazima
Ainaenum
Chaguomsingi95s
95s285s
Urefu wa muziki utakaotengenezwa.
cfg_strengthsi lazima
Ainanumber
Chaguomsingi4
1 – 10
Nguvu ya CFG inayotumika wakati wa kutengeneza muziki.
schedulersi lazima
Ainaenum
Chaguomsingieuler
eulermidpointrk4implicit_adams
Scheduler inayotumika wakati wa kutengeneza muziki.
num_inference_stepssi lazima
Ainainteger
Chaguomsingi32
10 – 100
Idadi ya hatua za inference za kutengeneza muziki.
inahitajika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

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"
  }
}
Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.
Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.
Sehemu za tokeo
audio
object {url, content_type, file_name, file_size}Faili iliyo na muziki uliotengenezwa.

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/diffrhythm.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt