Kling AI Avatar v2 Pro

Endpoint

POST https://api.roasos.com/v1/lipsync/kling-avatar-v2-pro

Send your API key as a bearer token. The key needs the scope api:write. Every paid request also needs an Idempotency-Key header.

The envelope fields quote_only, quote_id, webhook_url and wait_timeout_seconds behave the same on each model endpoint. Refer to Jobs and Quotes and credits.

Good at

A 30-second spokesperson read where the face must stay stable and expressive. An optional prompt steers the scene; the fal default "." means no steering. It is the premium model of the family and it costs the most per second. It does not take a video source and it does not accept aspect ratio or resolution controls.

Pricing

The unit is one second. Pricing key: kling-avatar-v2-pro.

The credits come from the roasOS pricing table. No other field changes the price. To get the exact price of your request, send it with quote_only: true first.

Modes

• image-audio-to-video

Provider endpoints: fal-ai/kling-video/ai-avatar/v2/pro.

Request fields

The schema is strict. A field that is not in this table gets 400 unsupported_option. The field names are the roasOS role names. One role has one name in every family.

Media

This endpoint accepts these media roles:

• avatar_id — identity; the saved character reference sheet, with a derived portrait only where the model requires a single face or source frame
• image_url — first frame (or the single source image)
• audio_url — the driving audio track

Every other role is refused: elements, product_id, product_images, references, reference_images, end_image_url, scene_id, scene_image, video_urls, video_url, audio_urls, voice_id. A refused role gets 400 unsupported_option.

Prompt

• Limit 2,500 characters. Sent verbatim; no wrapper.
• Omit it for a plain read; the fal default applies.
• When you steer, name one setting and one mood: "warm studio light, calm delivery".
• Do not write the words; the audio carries them.

Not exposed

roasOS pins no provider field for this model.

Result

The result kind is lipsync. Always present: url.

{
  "data": {
    "id": "gen_…",
    "kind": "lipsync",
    "model": "kling-avatar-v2-pro",
    "status": "completed",
    "result": {
      "url": "https://cdn.roasos.com/workspaces/ws_01/result"
    }
  }
}

The files are immutable objects on https://cdn.roasos.com. A result URL is a valid media input for your next request.

Example

The three steps are always the same: quote, run, poll.

# 1. Quote. Nothing is spent.
curl -X POST https://api.roasos.com/v1/lipsync/kling-avatar-v2-pro \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-kling-avatar-v2-pro-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_only":true,"audio_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/audio_url.mp3","image_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/image_url.png","media_rights":{"accepted":true,"statement_version":1}}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 14, "expires_at": "...",
#        "confirmation": { "model": "kling-avatar-v2-pro", "example": "10s" } } }

# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/lipsync/kling-avatar-v2-pro \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-kling-avatar-v2-pro-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_id":"q_7Hk...","audio_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/audio_url.mp3","image_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/image_url.png","media_rights":{"accepted":true,"statement_version":1}}'
# 201 { "data": { "id": "gen_...", "status": "queued", "credits_reserved": 14 } }

# 3. Poll, then read the result.
curl https://api.roasos.com/v1/jobs/gen_.../status -H "Authorization: Bearer roasos_sk_live_..."
curl https://api.roasos.com/v1/jobs/gen_.../result -H "Authorization: Bearer roasos_sk_live_..."

The deprecated path

POST /v1/generations still reaches this model for one minor version. It is deprecated. This is how it maps:

Not available on the public API. The contract of POST /v1/lipsync/kling-avatar-v2-pro is frozen and the route answers 501 model_endpoint_not_implemented: the model needs a recorded media-rights attestation and a server-measured audio duration, and the public API captures neither yet. POST /v1/generations returns 503 lipsync_public_authority_unavailable for the same reason. The app route POST /api/generate/lipsync with model: "kling-avatar-v2-pro" and rights_accepted: true reaches the provider.

See also

• llms.txt for this model — the same facts as one plain-text file for an agent.
• GET https://api.roasos.com/v1/catalog/kling-avatar-v2-pro — the machine-readable form: enums, defaults, limits and prices. Refer to the API reference.
• Jobs — how to poll a job and read its result.
• Provider endpoints: fal-ai/kling-video/ai-avatar/v2/pro.