Kwaivgi Kling V1 Ai Avatar Standard

Playground

Kling AI Avatar produces stunning AI-generated video avatars for digital identity and content creation, with on-demand video billed at $0.25 per 5 seconds. Ready-to-use REST API, no coldstarts, affordable pricing.

Features

Kuaivgi Kling v1 AI Avatar Standard — Audio-Driven Talking Portrait

Turn a single portrait into a natural talking-head video driven by your audio. The Standard tier focuses on clean lip-sync and stable identity at a budget-friendly rate—great for explainers, support avatars, internal training, and product demos.

Highlights

Phoneme-aligned lip-sync with natural eye blinks and head motion
Identity-preserving generation from one image
Works with real recordings or TTS audio
Optional prompt to nudge framing, background vibe, or style
Fast, reliable outputs suitable for everyday production

Parameters

audio (required): speech track; duration determines the clip length
image (required): clear, front-facing portrait (URL or upload)
prompt (optional): short guidance for mood, background, or framing

Recommended inputs

Portrait: even lighting, minimal occlusion, 512 px or larger
Audio: clean voice, 16–48 kHz, avoid heavy music/reverb

How to Use

Upload or paste the audio URL.
Upload or paste the portrait image URL.
(Optional) Add a brief prompt to describe background tone or framing.
Press Run and download the generated avatar video.

Tips

Trim long silences to reduce cost and tighten pacing.
Keep headroom consistent across images if you plan a series.
Use a high-quality mic or TTS for crisp consonants and better lip-sync.

Pricing

Price per second: $0.05

Billing rules

Minimum charge: 5 seconds.
Maximum billable length: 600 seconds (10 minutes) → $30.00 cap.
Currency rounding: totals are rounded to the nearest cent.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v1-ai-avatar-standard" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
audio	string	Yes	-	-	The audio for generating the output.
image	string	Yes		-	The image for generating the output.
prompt	string	No		-	The positive prompt for the generation.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Kwaivgi Kling V1 AI Avatar Pro Kwaivgi Kling V1 Tts