audiostringrequired
Input audio URL.
HeyGen Lipsync Precision
heygen/lipsync/precisionHeyGen v3 Lipsync (precision) replaces the speech in a video and re-syncs the speaker's lips to the new audio.
Try the model
Playground
Input
Input audio URL.
Input video URL.
Additional Settings More
Customize your input with more control.
End time (seconds) for partial lipsync. Minimum: 0.
Start time (seconds) for partial lipsync. Minimum: 0.
Burn in captions.
Remove background music from the source video.
Allow the video length to follow the new audio.
Enhance the replacement audio.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "audio": "https://static.sandbase.ai/examples/3c0d2094-8315-4f9f-bfbd-1a209d8ab9e0/input/733399b2-2dc9-4da1-93ed-5b156997b3c6.mp3", "video": "https://static.sandbase.ai/examples/3c0d2094-8315-4f9f-bfbd-1a209d8ab9e0/input/c517493c-b3d5-4f92-be2f-684336862d50.mp4" }
HeyGen Lipsync Precision
HeyGen Lipsync (precision) replaces the speech in a video and re-syncs the speaker's lips to new audio. Precision gives the best sync.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
video | video URL, required | — | Video with the speaker. |
audio | audio URL, required | — | New speech. |
disable_music_track | boolean | false | Drop background music. |
enable_caption | boolean | false | Burn in captions. |
enable_dynamic_duration | boolean | true | Adjust video length to the new audio. |
enable_speech_enhancement | boolean | false | Clean up the new speech. |
end_time | number | — | Optional end of the section. |
start_time | number | — | Optional start of the section to sync (seconds). |
Billing
$0.10 per output second. The quote before submission assumes 5 seconds.
| Output | Price |
|---|---|
| 5s | $0.50 |
| 30s | $3.00 |
| 60s | $6.00 |
Failed runs are not charged.
Also on SandBase
Related: heygen/lipsync/speed, sync/lipsync/3.0/video-to-video.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "heygen/lipsync/precision",
"audio": "https://v3.fal.media/files/rabbit/Ql3ade3wEKlZXRQLRbhxm_tts.mp3",
"video": "https://media.sandbase.ai/files/922d1013-9018-4956-a39d-d0859149ba76/0.mp4",
"enable_caption": false,
"disable_music_track": false,
"enable_dynamic_duration": true,
"enable_speech_enhancement": false
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
videostringrequired
Input video URL.
end_timenumber
End time (seconds) for partial lipsync.
Minimum: 0
start_timenumber
Start time (seconds) for partial lipsync.
Minimum: 0
enable_captionboolean
Burn in captions.
Default: false
disable_music_trackboolean
Remove background music from the source video.
Default: false
enable_dynamic_durationboolean
Allow the video length to follow the new audio.
Default: true
enable_speech_enhancementboolean
Enhance the replacement audio.
Default: false
{
"model": "heygen/lipsync/precision",
"audio": "https://v3.fal.media/files/rabbit/Ql3ade3wEKlZXRQLRbhxm_tts.mp3",
"video": "https://media.sandbase.ai/files/922d1013-9018-4956-a39d-d0859149ba76/0.mp4",
"enable_caption": false,
"disable_music_track": false,
"enable_dynamic_duration": true,
"enable_speech_enhancement": false
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/160849037f6b829828c6.jpg",
"source": "heygen schema mirror",
"source_url": "https://heygen.example/",
"url": "https://static.sandbase.ai/examples/3c0d2094-8315-4f9f-bfbd-1a209d8ab9e0/output/2c878a19-1725-4c94-adc2-1a59986d8302.mp4"
}
]