Peke ki ngā ihirangi

Wan-2.2 Speech-to-Video 14B

Whakauru

id tauira wan/v2.2-14b/speech-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/wan/v2.2-14b/speech-to-video?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",
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "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://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Ngā kōnae pēnei i te tauira: $ 0.50 500 whiwhinga API ka inea ō kōnae i mua i te whakahaere Whakahaerehia ki tēnei whārangi

Tikina he kī API
Alibaba Tukutahi Ngutu me ngā Avatar Tukutahi Ngututae atu ki 720p #audio-to-video#talking-head

Ka hanga ataata kōrero mai i tētahi atahanga tū tonu me tētahi kōnae ororongo, ka ārahina e tētahi tohutohu kuputuhi

Alibaba · Ataata

Kei konei tō hua tuatahi

Hangaia he tono ki raro nei, ka whakahaere mā tō kī API. Ka tāruatia ngā putanga ki tō mātou rokiroki, ka puritia mō ake tonu atu, mō rānei 7 rā mō te kore utu.

Hangaia he tono

Ka hangaia ngā mana whakahaere mai i te aronuinga o te tauira. Ka whakahoungia te waehere me te utu ina whakarerekē koe.

•e hiahiatia ana

Te tohutohu kuputuhi i whakamahia hei whakaputa i te ataata.

•e hiahiatia ana image_url
Whakataka he kōnae,

URL atahanga pūtake, ā, mā te ōwehenga āhuatanga kua kōwhiria e whakatau mēnā me tukatuka-mua: mā te rerekētanga ka rahi anō, kātahi ka tapahia te pokapū.

•e hiahiatia ana audio_url
Whakataka he kōnae,

URL e tohu ana ki te kōnae ororongo.

resolution taunoa 480p

Te taumira ataata putanga: 480p, 580p, 720p rānei.

taunoa 80

Kōwhiria he whakareatanga o te 4 i waenga i te 40–120 hei tautuhi i te maha o ngā anga ka whakaputaina.

Arā atu negative_prompt · video_quality · video_write_mode · frames_per_second · num_inference_steps · guidance_scale · shift · seed · enable_safety_checker · enable_output_safety_checker
taunoa

Te tohutohu tōraro e whakamahia ana i te whakaputa ataata.

video_quality taunoa high

Te tautuhinga kounga ataata putanga, e whakawhiti ana i te rahi ake o te kōnae mō ngā āhua pai ake ina piki te tautuhinga.

video_write_mode taunoa balanced

Te aratau tuhi ataata, ko balanced te taurite i waenga i te tere me te kounga. Kōwhiria small mō ngā kōnae iti rawa me te tuhi pōturi rawa; mā te tuhi tere ake ka hoki wawe mai ngā hua, engari ka nui ake ngā kōnae.

taunoa 16

Te auau anga ataata kua whakaputaina, e whakaae ana ki ngā uara mai i te 4 ki te 60; mā te tautuhi `adjust_fps_for_interpolation` ki false ka pupuri tonu i tēnei auau. Ina whakamahia te whakanuitanga, ā, ko te taunoa o `adjust_fps_for_interpolation` he true, whakareatia tēnei auau ki te kotahi tāpirihia ki te maha o ngā anga kua whakanuitia hei whiwhi i te FPS whakamutunga. Hei tauira, ka huri te 16 FPS me te 1 anga kua whakanuitia ki te 32 FPS.

taunoa 27

Te tatau kaupae tīpako, ka whakawhiti i te wā tukatuka roa mō te kounga pai ake ina piki te tatau.

taunoa 3.5

Te kaha arataki classifier-free, ka whakawhiti i te ngaronga kounga pea mō te ū tata ake ki te tohutohu ina piki te tauine.

taunoa 5

Te tautuhinga neke ataata, he awhe whakaaetia 1.0–10.0.

Te kākano e taea ai te tārua o te whakaputanga. Mā te tautuhi ki None e kōwhiri matapōkeretia ai he kākano.

POST /run/wan/v2.2-14b/speech-to-video?wait=20 utu → $ 0.50
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/wan/v2.2-14b/speech-to-video?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",
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "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://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Whakahaerehia tēnei tono

Ka noho tō kī ki tēnei pūtirotiro: ka tukuna ki te Doitong API anake, ā, ka tiakina ki te localStorage anake ina tohua e koe te Mahara. Tikina he kī API

Mō Wan-2.2 Speech-to-Video 14B

Me whai `prompt`, `image_url` pūtake me `audio_url`, ā, ka whakaputa ataata o te kaupapa kei te atahanga, ka aratakina e te ororongo. Kei waenga `num_frames` i te 40 me te 120, he whakarea o te 4, ā, ko te taunoa he 16 fps. Ka taea `resolution` te 480p, 580p, 720p rānei. Ka taea te whakatika i ngā hipanga tīpako, te arataki, te whakawhitinga me tētahi `negative_prompt`.

Ngā tawhā

Tukuna te ingoa tōmua, te ingoa taketake rānei, kaua e rua. Ngā ingoa tōmua

IngoaMomo TaunoaE whakaaetia ana Whakamārama
prompte hiahiatia ana
Momostring
Te tohutohu kuputuhi i whakamahia hei whakaputa i te ataata.
negative_promptkōwhiringa
Momostring
Taunoa
Te tohutohu tōraro e whakamahia ana i te whakaputa ataata.
num_frameskōwhiringa
Momointeger
Taunoa80
40 – 120
Kōwhiria he whakareatanga o te 4 i waenga i te 40–120 hei tautuhi i te maha o ngā anga ka whakaputaina.
frames_per_secondkōwhiringa
Momointeger | null
Taunoa16
4 – 60
Te auau anga ataata kua whakaputaina, e whakaae ana ki ngā uara mai i te 4 ki te 60; mā te tautuhi `adjust_fps_for_interpolation` ki false ka pupuri tonu i tēnei auau. Ina whakamahia te whakanuitanga, ā, ko te taunoa o `adjust_fps_for_interpolation` he true, whakareatia tēnei auau ki te kotahi tāpirihia ki te maha o ngā anga kua whakanuitia hei whiwhi i te FPS whakamutunga. Hei tauira, ka huri te 16 FPS me te 1 anga kua whakanuitia ki te 32 FPS.
seedkōwhiringa
Momointeger | null
Te kākano e taea ai te tārua o te whakaputanga. Mā te tautuhi ki None e kōwhiri matapōkeretia ai he kākano.
resolutionkōwhiringa
Momoenum
Taunoa480p
480p580p720p
Te taumira ataata putanga: 480p, 580p, 720p rānei.
num_inference_stepskōwhiringa
Momointeger
Taunoa27
2 – 40
Te tatau kaupae tīpako, ka whakawhiti i te wā tukatuka roa mō te kounga pai ake ina piki te tatau.
enable_safety_checkerkōwhiringa
Momoboolean
Taunoafalse
Te tirotiro haumaru tāuru i mua i te tukatuka, ā, ko ngā pūkete whai mana anake ka taea te whakaweto. Ka tirotirohia tonutia ngā tono kāore he mana; ki te whai mana, mā true e whakahohe te tirotiro.
enable_output_safety_checkerkōwhiringa
Momoboolean
Taunoafalse
Ka whakahaere i te tirotiro haumaru o te ataata kua whakaputaina; mā te tautuhi true e whakahohe te tirotiro i muri i te whakaputanga.
guidance_scalekōwhiringa
Momonumber
Taunoa3.5
1 – 10
Te kaha arataki classifier-free, ka whakawhiti i te ngaronga kounga pea mō te ū tata ake ki te tohutohu ina piki te tauine.
shiftkōwhiringa
Momonumber
Taunoa5
1 – 10
Te tautuhinga neke ataata, he awhe whakaaetia 1.0–10.0.
video_qualitykōwhiringa
Momoenum
Taunoahigh
lowmediumhighmaximum
Te tautuhinga kounga ataata putanga, e whakawhiti ana i te rahi ake o te kōnae mō ngā āhua pai ake ina piki te tautuhinga.
video_write_modekōwhiringa
Momoenum
Taunoabalanced
fastbalancedsmall
Te aratau tuhi ataata, ko balanced te taurite i waenga i te tere me te kounga. Kōwhiria small mō ngā kōnae iti rawa me te tuhi pōturi rawa; mā te tuhi tere ake ka hoki wawe mai ngā hua, engari ka nui ake ngā kōnae.
image_urle hiahiatia ana image
Momourl · image
URL atahanga pūtake, ā, mā te ōwehenga āhuatanga kua kōwhiria e whakatau mēnā me tukatuka-mua: mā te rerekētanga ka rahi anō, kātahi ka tapahia te pokapū.
audio_urle hiahiatia ana audio
Momourl · audio
URL e tohu ana ki te kōnae ororongo.
e hiahiatia ana Ingoa tōmua, e whakaaetia ana hoki

Mō ngā tawhā kōnae, whakamahia he URL tūmatanui https://, he URI data: tae atu ki te 10 MB, he file_url rānei o tētahi tukuake. Ngā kōnae

Putanga

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "wan/v2.2-14b/speech-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": 500,
    "usd": "0.50",
    "charged": 500,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "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
    }
  },
  "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://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Ō kōnae, māu e whiriwhiriKo ia url o outputs[] he tārua kei tō mātou rokiroki: ka puritia mō ake tonu atu (ka utua ia GB-marama) mō rānei 7 rā mō te kore utu, e ai ki ngā tautuhinga o tō pūkete, ki te ?storage= rānei.
He ōrite te hanga ki ia tauiratype, url, content_type, width, height me duration, mō ngā pikitia, ataata me te oro. Ko output te ahanoa hua ake o te tauira.
Ngā āpure o te putanga
video
object {url, content_type, file_name, file_size}Te kōnae ataata i whakaputaina.

Ētahi atu tauira: Tukutahi Ngutu me ngā Avatar

Mō ngā āpiha AI: kei te wātea tēnei whārangi hei Markdown ki https://doitong.com/mi/developers/models/wan/v2.2-14b/speech-to-video.md. Ngā tauira me ngā aratohu katoa: https://doitong.com/developers/llms.txt