Kling: video generation API

{ "url": "https://cdn.example.com/file.png" }

{ "file_id": "your-file-id" }

{
  "model": "kling-v3-omni",
  "prompt": "<<<element_1>>> and <<<element_2>>> rotate slowly on a clean studio table",
  "duration": 5,
  "resolution": "1080p",
  "images": [
    { "url": "https://cdn.example.com/first.png", "usage": "first_frame" },
    { "file_id": "last-frame-file-id", "usage": "last_frame" },
    { "url": "https://cdn.example.com/reference-a.png", "usage": "reference" }
  ]
}

{
  "videos": [
    {
      "url": "https://cdn.example.com/character-motion.mp4",
      "reference_type": "feature",
      "keep_original_sound": false
    }
  ]
}

{
  "subjects": [
    { "id": "subject-92951593344", "name": "cat" },
    { "id": "subject-92951593345", "name": "dog" }
  ]
}

{
  "model": "kling-v3-omni",
  "prompt": "A short product story in two shots",
  "duration": 5,
  "shots": {
    "mode": "customize",
    "segments": [
      { "index": 1, "prompt": "The box opens", "duration": 2 },
      { "index": 2, "prompt": "The product is revealed", "duration": 3 }
    ]
  }
}

{
  "model": "kling-v3-motion-control",
  "prompt": "Follow the dancer's movement",
  "resolution": "1080p",
  "images": [{ "file_id": "person-image-file-id" }],
  "videos": [{ "url": "https://cdn.example.com/dance.mp4", "keep_original_sound": true }],
  "extra": { "character_orientation": "video" }
}

curl https://api.hop-base.com/v1/kling/faces \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{"videos":[{"file_id":"source-video-file-id"}]}'

{
  "model": "kling-lip-sync",
  "extra": {
    "session_id": "face-session-id",
    "face_choose": [
      { "face_id": "face-1", "sound_file": "https://cdn.example.com/voice.mp3" }
    ]
  }
}

{
  "id": "ktEXAMPLE",
  "object": "video.generation.task",
  "model": "kling-v3",
  "status": "queued",
  "created": 1790000000,
  "billing_bucket": "720p_silent_noref"
}

{
  "id": "ktEXAMPLE",
  "object": "video.generation.task",
  "model": "kling-v3",
  "status": "processing",
  "created": 1790000000
}

{
  "id": "ktEXAMPLE",
  "status": "completed",
  "outputs": [
    "https://api.hop-base.com/example-signed-image.png"
  ],
  "usage": { "bucket": "720p_silent_noref", "billed_seconds": 5, "cost": 2.55, "cost_usd": 0.375, "currency": "CNY" }
}

{
  "id": "ktEXAMPLE",
  "object": "video.generation.task",
  "model": "kling-v3",
  "status": "failed",
  "created": 1790000000,
  "error": {
    "code": "timeout",
    "message": "task did not reach a billable terminal state within 2 hours; polling stopped"
  }
}

{
  "error": {
    "message": "request body does not match the JSON contract: json: unknown field \"size\"",
    "type": "invalid_request_error"
  }
}

# An image model sent to the video endpoint (400)
model "<model ID>" is an image model; use /v1/images/generations

# Video model ID not in the catalog (404)
model "<model ID>" is not in the Kling catalog

# Image model ID not in the catalog (404)
model "<model ID>" is not an image model in this catalog

# Media item with neither or both of url / file_id
<images or videos>[<index>] must provide exactly one of url or file_id

# url that is not a public absolute http(s) address
<images or videos>[<index>].url must be a publicly accessible absolute http(s) URL

# No prompt and no media at all (except lip sync)
prompt and input media cannot both be empty

# Negative duration
duration cannot be negative

# duration outside the model range
model <model ID> supports <min> to <max> seconds, got <value>

# kling-o1 without reference inputs and a duration other than 5 or 10
Kling O1 without reference media only supports duration 5 or 10 seconds

# kling-v2-6 with a duration other than 5 or 10
model kling-v2-6 only supports a duration of 5 or 10 seconds, got <value>

# aspect_ratio other than 16:9 / 9:16 / 1:1
aspect_ratio="<value>" is invalid; allowed values: 16:9 / 9:16 / 1:1

# No price tier for the resolution / audio / reference-video combination
model "<model ID>" does not support billing bucket "<tier>" for this request

# Non-empty voice_ids (the message starts with this)
voice_ids is not available yet

# An extra key this model does not accept
extra.<key> is not in the verified parameter contract of model <model ID>

# duration sent to a model whose length comes from the input
duration of model <model ID> is determined by the input media; do not pass duration

# Missing or invalid usage
images[<index>].usage is required for standard Kling video requests
images[<index>].usage="<value>" is invalid; allowed values: first_frame / last_frame / reference

# First- and last-frame rules
at most 1 first-frame image is allowed
at most 1 last-frame image is allowed
a last frame requires a first frame with usage=first_frame
Kling 2.1 first/last-frame generation only supports 1080p
a last frame is not supported with more than 2 reference images (got <count>)

# Reference image counts
with a reference video, reference images + subjects cannot exceed 4, got <total> (<images> images + <subjects> subjects)
without a reference video, reference images + subjects cannot exceed 7, got <total> (<images> images + <subjects> subjects)
model <model ID> supports at most <max> reference images, got <count>
model <model ID> does not support reference-based generation

# Missing or invalid reference_type, or more than 1 video
videos[0].reference_type is required for standard Kling video requests; allowed values: feature / base
videos[<index>].reference_type="<value>" is invalid; allowed values: feature / base
standard Kling video requests accept at most 1 videos input

# Reference video type not supported by the model, or base mixed with images / subjects
model <model ID> has no confirmed feature reference-video capability or price tier
model <model ID> has no confirmed base video-edit price tier
base video edit cannot be combined with images or subjects; only a single video to edit is accepted

# Original-sound parameter inside extra
extra.keep_original_sound cannot be passed through; use videos[].keep_original_sound

# Motion control
motion control requires exactly 1 motion video and 1 character image
motion control images[<index>] does not accept usage; the character image role is fixed by the scene
motion control videos[<index>] does not accept reference_type; the motion video role is fixed by the scene
extra.character_orientation must be image or video

# Avatar
Kling avatar requires at least 1 character image
model <model ID> supports at most 5 character images, got <count>
Kling avatar does not accept videos input
Kling avatar requires exactly one of extra.sound_file or extra.audio_id
extra.sound_file must be a non-empty string
extra.audio_id must be a non-empty string
extra.sound_file must be a publicly accessible http(s) audio URL

# Face detection: invalid JSON or any other field
request body does not match the JSON contract: …

# Face detection: missing or empty videos
videos is required and must contain at least one item

# Lip sync
Kling lip-sync does not accept images or videos; use extra.session_id and extra.face_choose
Kling lip-sync requires a non-empty extra.session_id
Kling lip-sync requires an extra.face_choose array with exactly 1 item
extra.face_choose[0].<key> is not part of the lip-sync contract
extra.face_choose[0].face_id must be a non-empty string or a non-negative integer
extra.face_choose[0].sound_file must be a non-empty string
extra.face_choose[0].sound_file must be a publicly accessible http(s) audio URL
extra.voice_list is reserved; use voice_ids instead (voice selection is not available yet)

# input_sensitive: prompt refused by moderation
the prompt was rejected by content moderation; rephrase it and submit again

# input_sensitive: reference media refused by moderation
the reference media was rejected by content moderation; replace it and submit again

# input_sensitive: moderation, source not reported
the prompt or reference media was rejected by content moderation; revise it and submit again

# output_video_sensitive / safety_rejected: output blocked by moderation
the generated result was blocked by content moderation; adjust the prompt or reference media and submit again

# rate_limited: concurrency ceiling reached
this model is at its concurrency limit right now; please retry shortly

# unsupported_model: model version retired
this model version is no longer available; switch to another model and submit again

# invalid_request: prompt too long
the prompt is too long for this model (at most 2500 characters); shorten it and submit again

# invalid_request: parameters or media rejected
the request was rejected as invalid by the model; check the parameters and media against the documented limits, then submit again

# reference_input_invalid: reference media unreadable
a reference image or video is missing or could not be read; make sure every URL is publicly reachable and points to a supported file, then submit again

# generation_failed: generation failed (other)
video generation failed; please retry, and contact support with the task ID if it keeps failing

# generation_failed: stopped before finishing
video generation was stopped before it finished; please retry, and contact support with the task ID if it keeps failing

# generation_failed: task could not be tracked (ends with this)
… contact support with the task ID

# timeout: still unfinished 2 hours after creation
task did not reach a billable terminal state within 2 hours; polling stopped

# timeout: custom subject still unfinished after 2 hours
subject task did not reach a terminal state within 2 hours; polling stopped

# no_output: task ended with no output
video generation finished without a usable output; please retry, and contact support with the task ID if it keeps failing

# no_output: custom subject ended without a subject ID
subject creation finished without returning a subject ID; check the media and create it again