Skip to content

Kling LipSync Text-to-Video

Integrate

Model id kling-video/lipsync/text-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/kling-video/lipsync/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "voice_id": "genshin_vindi2"
  }'

# 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"

Files like the example: $0.14 140 API credits · ≈ ₽15.02 your files are measured before the run Run it on this page

Get API key
Kling Lipsync & Avatars Lipsync #text-to-video

Makes a person in a video speak typed text using a selectable synthetic voice, with adjustable speed

Made on Doitong

Public works made with Kling LipSync by the Doitong community. Reuse a prompt in one click.

Public works shown: 16
Video

You didn't fail because you're weak. You failed because you QUIT the second it got uncomfortable. Comfort is the enemy. Comfort is the drug that's keeping you average. Nobody's coming to save you. YOU are the rescue mission. Tomorrow morning, five A M. Do the thing you've been avoiding. That's...

Video

Как остановить тревогу за 60 секунд. Когда она накатывает, начните с дыхания: медленно вдохните через нос на четыре счёта, задержите на четыре и мягко выдохните через рот на шесть. Повторите три раза — это сразу успокаивает нервную систему. Затем посмотрите вокруг и вслух назовите три вещи,...

Video

You didn't fail because you're weak. You failed because you QUIT the second it got uncomfortable. Comfort is the enemy. Comfort is the drug that's keeping you average. Nobody's coming to save you. YOU are the rescue mission. Tomorrow morning, five A M. Do the thing you've been avoiding. That's...

Video

Дорогой друг, если тревога внезапно накрыла, остановите её за шестьдесят секунд тремя простыми шагами. Сначала медленно вдохните носом на четыре секунды, задержите дыхание ещё на четыре и плавно выдохните ртом на шесть. Это сразу снижает активность симпатической нервной системы и даёт телу сигнал...

Video

You didn't fail because you're weak. You failed because you QUIT the second it got uncomfortable. Comfort is the enemy. Comfort is the drug that's keeping you average. Nobody's coming to save you. YOU are the rescue mission. Tomorrow morning, five A M. Do the thing you've been avoiding. That's...

Video

You didn't fail because you're weak. You failed because you QUIT the second it got uncomfortable. Comfort is the enemy. Comfort is the drug that's keeping you average. Nobody's coming to save you. YOU are the rescue mission. Tomorrow morning, five A M. Do the thing you've been avoiding. That's...

Video

You didn't fail because you're weak. You failed because you QUIT the second it got uncomfortable. Comfort is the enemy. Comfort is the drug that's keeping you average. Nobody's coming to save you. YOU are the rescue mission. Tomorrow morning, five A M. Do the thing you've been avoiding. That's...

Video

Как перестать всё контролировать? Я знаю, как тяжело постоянно держать всё в руках. Вот три простых шага, которые реально помогают. Сначала заметьте, когда внутри возникает напряжение, и сделайте три медленных выдоха длиннее вдохов. Это сразу включает спокойную часть нервной системы. Второй шаг:...

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required 88 / 120

Text used to generate a lip-sync video, limited to 120 characters.

•required video_url
Drop a file, or

Video URL for lip-sync generation. Accepts .mp4 or .mov files up to 100MB, lasting 2–60s, at 720p or 1080p only; both dimensions must fall within 720–1920px. Validation failure returns an error.

•required

Identifier of the voice used to synthesize speech.

Advanced voice_language · voice_speed · enable_safety_checker
voice_language default en

Language associated with the selected Voice ID.

default 1

Speaking speed used when generating video from text.

POST /run/kling-video/lipsync/text-to-video?wait=20 quote → $0.14
# 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/kling-video/lipsync/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "voice_id": "genshin_vindi2"
  }'

# 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"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Kling LipSync Text-to-Video

Generates lip-synced speech from text instead of an audio file. Provide `video_url`, up to 120 characters of `text`, and a `voice_id` chosen from a list of preset voices. `voice_language` is either zh or en, and `voice_speed` ranges from 0.8 to 2. The source video can be .mp4 or .mov, up to 100MB, 2 to 60 seconds, at 720p or 1080p.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Safety checks can be disabled only with account authorization; requests without authorization always undergo checking.
video_urlrequired video
Typeurl · video
Video URL for lip-sync generation. Accepts .mp4 or .mov files up to 100MB, lasting 2–60s, at 720p or 1080p only; both dimensions must fall within 720–1920px. Validation failure returns an error.
textrequired
Typestring
≤ 120 characters
Text used to generate a lip-sync video, limited to 120 characters.
voice_idrequired
Typeenum
genshin_vindi2zhinen_xueshengAOTai_shatanggenshin_klee2genshin_kiraraai_kaiyaoversea_male1ai_chenjiahao_712girlfriend_4_speech02chat1_female_new-3chat_0407_5-1cartoon-boy-07uk_boy1cartoon-girl-01PeppaPig_platform
+30 moreai_huangzhong_712ai_huangyaoshi_712ai_laoguowang_712chengshu_jiejieyou_pingjingcalm_story1uk_man2laopopo_speech02heainainai_speech02reader_en_m-v1commercial_lady_en_f-v1tiyuxi_xueditiexin_nanyougirlfriend_1_speech02girlfriend_2_speech02zhuxi_speech02uk_oldman3dongbeilaotie_speech02chongqingxiaohuo_speech02chuanmeizi_speech02chaoshandashu_speech02ai_taiwan_man2_speech02xianzhanggui_speech02tianjinjiejie_speech02diyinnansang_DB_CN_M_04-v2yizhipiannan-v1guanxiaofang-v2tianmeixuemei-v1daopianyansang-v1mengwa-v1
Identifier of the voice used to synthesize speech.
voice_languageoptional
Typeenum
Defaulten
zhen
Language associated with the selected Voice ID.
voice_speedoptional
Typenumber
Default1
0.8 – 2
Speaking speed used when generating video from text.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "kling-video/lipsync/text-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": 140,
    "usd": "0.14",
    "charged": 140,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "voice_id": "genshin_vindi2"
  },
  "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://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
video
object {url, content_type, file_name, file_size}Video produced by the model.

More models: Lipsync & Avatars

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/kling-video/lipsync/text-to-video.md. All models and guides: https://doitong.com/developers/llms.txt