Ruka hadi kwenye maudhui

Longcat Single Avatar · Audio to Video

Unganisha

Kitambulisho cha modeli longcat-single-avatar/audio-to-video
# 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/longcat-single-avatar/audio-to-video?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"

Faili kama mfano: $ 0.90 salio za API 900 · ≈ ₽ 96.82 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Meituan Usawazishaji wa Midomo na Avatari Usawazishaji wa midomohadi 720p #audio-to-video

Huunda video ya avatari inayozungumza inayoendeshwa na faili la sauti na kidokezo cha maandishi pekee, bila picha chanzo

Meituan · Video

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.

chaguomsingi A person is talking n...

Kidokezo kinachoelekeza uzalishaji wa video.

•inahitajika audio_url
Dondosha faili, au

URL ya faili ya sauti inayotumika kuendesha avatar.

resolution chaguomsingi 480p

Mwonekano wa video ya tokeo, ama 480p au 720p.

chaguomsingi 1

Idadi ya vipande vya video, ikiwa takriban 5.8s kwa kipande cha mwanzo na 5s kwa kila kipande kinachofuata—takriban sekunde 5 za video kwa kila kipande.

Ya kina negative_prompt · num_inference_steps · text_guidance_scale · audio_guidance_scale · seed · enable_safety_checker · enable_prompt_expansion
chaguomsingi Close-up, Bright tone...

Kidokezo hasi kinachobainisha kile ambacho uzalishaji wa video unapaswa kuepuka.

chaguomsingi 50

Idadi ya hatua za uelekezaji zilizotekelezwa.

chaguomsingi 4

Mizani ya mwongozo wa maandishi inayotumika katika mwongozo usio na kiainishaji.

chaguomsingi 4

Marekebisho ya mwongozo wa sauti ambayo yanaweza kuzidisha mwendo wa mdomo yanapoongezwa.

Thamani ya mbegu inayoanzisha uzalishaji wa nambari nasibu.

POST /run/longcat-single-avatar/audio-to-video?wait=20 makadirio → $ 0.90
# 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/longcat-single-avatar/audio-to-video?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"

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 Longcat Single Avatar · Audio to Video

Huunda video ya avatari yenye usawazishaji wa midomo kutoka `audio_url` na `prompt` inayoeleza mtu huyo. Tokeo ni 480p au 720p. `num_segments` (1 hadi 10) huweka urefu: fremu ya kwanza ni takriban sekunde 5.8 na kila nyingine huongeza sekunde 5. `audio_guidance_scale` (1 hadi 10) hudhibiti jinsi usemi unavyoendesha mdomo, na thamani za juu zinaweza kuzidisha mwendo.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
audio_urlinahitajika audio
Ainaurl · audio
URL ya faili ya sauti inayotumika kuendesha avatar.
promptsi lazima
Ainastring
ChaguomsingiA person is talking naturally with natural expressions and movements.
Kidokezo kinachoelekeza uzalishaji wa video.
negative_promptsi lazima
Ainastring
ChaguomsingiClose-up, Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards
Kidokezo hasi kinachobainisha kile ambacho uzalishaji wa video unapaswa kuepuka.
num_inference_stepssi lazima
Ainainteger
Chaguomsingi50
10 – 100
Idadi ya hatua za uelekezaji zilizotekelezwa.
text_guidance_scalesi lazima
Ainanumber
Chaguomsingi4
1 – 10
Mizani ya mwongozo wa maandishi inayotumika katika mwongozo usio na kiainishaji.
audio_guidance_scalesi lazima
Ainanumber
Chaguomsingi4
1 – 10
Marekebisho ya mwongozo wa sauti ambayo yanaweza kuzidisha mwendo wa mdomo yanapoongezwa.
resolutionsi lazima
Ainaenum
Chaguomsingi480p
480p720p
Mwonekano wa video ya tokeo, ama 480p au 720p.
num_segmentssi lazima
Ainainteger
Chaguomsingi1
1 – 10
Idadi ya vipande vya video, ikiwa takriban 5.8s kwa kipande cha mwanzo na 5s kwa kila kipande kinachofuata—takriban sekunde 5 za video kwa kila kipande.
seedsi lazima
Ainainteger | null
Thamani ya mbegu inayoanzisha uzalishaji wa nambari nasibu.
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Kigeuza ukaguzi wa usalama kinachotegemea ruhusa za akaunti: ukaguzi hubaki wa lazima kwa maombi yasiyoidhinishwa, na kuuzima kunahitaji uidhinishaji.
enable_prompt_expansionsi lazima
Ainaboolean
Chaguomsingifalse
Kigeuza upanuzi wa kidokezo unaotegemea LLM kwa kuboresha ubora wa video kupitia kidokezo kilichoboreshwa.
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": "longcat-single-avatar/audio-to-video",
  "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": 900,
    "usd": "0.90",
    "charged": 900,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "seed": 42
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "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"
  }
}
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
video
object {url, content_type, file_name, file_size}Faili ya video iliyozalishwa.
seed
integerThamani ya seed inayotumika wakati wa uzalishaji.

Miundo zaidi: Usawazishaji wa Midomo na Avatari

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/longcat-single-avatar/audio-to-video.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt