Ruka hadi kwenye maudhui

Stable Audio 25

Unganisha

Kitambulisho cha modeli stable-audio-25/inpaint
# 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/stable-audio-25/inpaint?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Ombi hili: $ 0.20 salio za API 200 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Stability AI Sauti #audio

Huzalisha upya kipindi cha muda chenye maski ndani ya klipu ya sauti kutoka kwenye kidokezo cha maandishi, huku ikihifadhi sehemu nyingine ya klipu

Stability AI · 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 kinachoelekeza uzalishaji wa sauti.

•inahitajika audio_url
Dondosha faili, au

Klipu ya sauti ya chanzo kwa ajili ya inpainting.

Ya kina seconds_total · guidance_scale · mask_start · mask_end · num_inference_steps · seed · enable_safety_checker
chaguomsingi 190

Urefu wa sauti ya tokeo huwa chaguomsingi kuwa urefu wa klipu ya ingizo. Toa urefu ili kubatilisha chaguo hilo.

chaguomsingi 1

Uaminifu wa sauti-kwa-kidokezo huongezeka kwa kuongeza mpangilio huu, unaoimarisha ufuataji wa maandishi katika mchakato wa diffusion.

chaguomsingi 30

Nafasi ya kuanzia ya barakoa ya sauti.

chaguomsingi 190

Nafasi ya kumalizia ya barakoa ya sauti.

chaguomsingi 8

Idadi ya hatua za kuondoa kelele zinazotumika kwenye sauti.

POST /run/stable-audio-25/inpaint?wait=20 makadirio → $ 0.20
# 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/stable-audio-25/inpaint?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "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.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 Stable Audio 25

Inpainting ya sauti: toa `audio_url` na `prompt`, kisha chagua eneo la kuandikwa upya kwa `mask_start` na `mask_end`, zote 0 hadi 190. Chaguo-msingi ni 30 na 190. `seconds_total` huanzia 1 hadi 190 na `guidance_scale` huanzia 1 hadi 25. `num_inference_steps` huwa 4 hadi 8, na `seed` huruhusu utekelezaji unaoweza kurudiwa.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo
promptinahitajika
Ainastring
Kidokezo kinachoelekeza uzalishaji wa sauti.
audio_urlinahitajika audio
Ainaurl · audio
Klipu ya sauti ya chanzo kwa ajili ya inpainting.
seconds_totalsi lazima
Ainainteger | null
Chaguomsingi190
1 – 190
Urefu wa sauti ya tokeo huwa chaguomsingi kuwa urefu wa klipu ya ingizo. Toa urefu ili kubatilisha chaguo hilo.
guidance_scalesi lazima
Ainanumber
Chaguomsingi1
1 – 25
Uaminifu wa sauti-kwa-kidokezo huongezeka kwa kuongeza mpangilio huu, unaoimarisha ufuataji wa maandishi katika mchakato wa diffusion.
mask_startsi lazima
Ainainteger
Chaguomsingi30
0 – 190
Nafasi ya kuanzia ya barakoa ya sauti.
mask_endsi lazima
Ainainteger
Chaguomsingi190
0 – 190
Nafasi ya kumalizia ya barakoa ya sauti.
num_inference_stepssi lazima
Ainainteger
Chaguomsingi8
4 – 8
Idadi ya hatua za kuondoa kelele zinazotumika kwenye sauti.
seedsi lazima
Ainainteger | null
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.
inahitajika Jina rasmi, pia linakubalika

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": "stable-audio-25/inpaint",
  "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": 200,
    "usd": "0.20",
    "charged": 200,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "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
    },
    "seed": 42
  },
  "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}Klipu ya sauti iliyozalishwa.
seed
integerSeed nasibu inayotumika wakati wa uzalishaji.

Miundo zaidi: Sauti

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/stable-audio-25/inpaint.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt