Veed Lipsync V2
Playground
Try it on WavespeedAI!VEED Lipsync V2 generates production-quality lip-synced videos from a source video and a replacement audio track, matching mouth movements to the new audio for dubbing, localization, creator content, and talking-video workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
VEED Lipsync V2
VEED Lipsync V2 generates production-quality lip-synced video from a source video and replacement audio track. Upload a video with a visible speaker, provide the new audio, and the model produces a video where the mouth movement follows the supplied audio.
Why Choose This?
-
Production-quality lipsync Generate natural mouth movement that follows the replacement audio track.
-
Simple video-to-video workflow Provide one source video and one audio file without extra tuning parameters.
-
Audio-driven duration The output video follows the uploaded audio duration.
-
Standard video output The generated video is returned as a URL in the standard WaveSpeed prediction response.
Parameters
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Source video containing the face to be lip-synced. |
| audio | Yes | Audio track that drives the mouth movement. |
How to Use
- Upload source video - Provide a video with a clear, visible face.
- Upload audio - Provide the replacement audio track.
- Submit - Generate the lip-synced video.
- Review output - The result is returned as a video URL.
Pricing
Pricing is $0.075 per second of uploaded audio duration, rounded up to the next full second.
| Audio Duration | Price |
|---|---|
| 5s | $0.375 |
| 10s | $0.75 |
| 30s | $2.25 |
| 60s | $4.50 |
Best Use Cases
- Video dubbing - Replace speech while keeping the original speaker video.
- Localization - Create translated versions of existing presenter videos.
- Dialogue replacement - Update spoken lines without reshooting footage.
- Marketing content - Adapt spokesperson videos for different messages.
- Education and training - Reuse presenter footage with new narration.
Pro Tips
- Use clear audio with minimal background noise.
- Use a source video where the mouth is visible and well-lit.
- Avoid heavy face occlusion or fast camera movement for best results.
- Match the style and pacing of the audio to the source footage when possible.
- Ensure both URLs are publicly accessible.
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/veed/lipsync-v2" \
--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 | - | - | Input audio URL. The output video follows the audio duration. |
| video | string | Yes | - | Input video URL containing the face to be lip-synced. |
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.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.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 |