seedinteger
Random seed for reproducibility.
Minimum: 0
Maximum: 2147483647
InfiniteTalk Video to Video
meigen/infinitetalk/video-to-videoInfiniteTalk dubs an existing video: it re-animates lips, face and body to match new speech audio.
Try the model
Playground
Input
Input audio URL.
Input video URL.
Text prompt guiding the generation.
Additional Settings More
Customize your input with more control.
Random seed for reproducibility. Range: 0 to 2147483647.
41241
Maximum frames to generate (41–241, 25 fps); output also stops at the end of the audio. Range: 41 to 241.
Output resolution (720p costs 2x). Allowed values: 480p, 720p.
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/b4b962b1-cb06-48d0-a0a4-6c0feb67c13b/input/1a1b7894-fdb9-4a3e-a8d7-67471c91d020.mp3", "num_frames": 41, "prompt": "A woman with colorful hair talking on a podcast.", "resolution": "480p", "video": "https://static.sandbase.ai/examples/b4b962b1-cb06-48d0-a0a4-6c0feb67c13b/input/07b54b85-765a-4454-ab0b-14620a533e1d.mp4" }
InfiniteTalk Video to Video
InfiniteTalk video-to-video dubs an existing clip, re-animating lips, face, and body to new speech.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Scene and gesture direction. |
video | video URL, required | — | Clip to re-animate. |
audio | audio URL, required | — | Speech that drives the lips. |
num_frames | integer 41–241 | 145 | Frames at 25fps when the length is not set by audio. |
resolution | 480p / 720p | 720p | Sets the per-second rate. |
seed | integer 0–2147483647 | random | Fix it to compare prompt changes. |
Billing
Per output second: $0.30 at 480p and $0.60 at 720p. Length follows the audio; without it, num_frames at 25fps (default 145 frames, 5.8 seconds).
| Output | 480p | 720p |
|---|---|---|
| 6s | $1.80 | $3.60 |
| 30s | $9.00 | $18.00 |
| 60s | $18.00 | $36.00 |
Failed runs are not charged.
Prompting
- Use a front-facing portrait with the mouth visible.
Also on SandBase
Other InfiniteTalk endpoints: meigen/infinitetalk/image-to-video, meigen/infinitetalk/text-to-video.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "meigen/infinitetalk/video-to-video",
"audio": "https://v3.fal.media/files/penguin/PtiCYda53E9Dav25QmQYI_output.mp3",
"video": "https://storage.googleapis.com/falserverless/model_tests/video_models/ref_video.mp4",
"prompt": "A woman with colorful hair talking on a podcast.",
"num_frames": 145,
"resolution": "720p"
}
SANDBASE_JSON
)
run_id=$(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
audiostringrequired
Input audio URL.
videostringrequired
Input video URL.
promptstringrequired
Text prompt guiding the generation.
num_framesinteger
Maximum frames to generate (41–241, 25 fps); output also stops at the end of the audio.
Default: 145
Minimum: 41
Maximum: 241
resolutionstring
Output resolution (720p costs 2x).
Default: "720p"
Possible values: "480p", "720p"
{
"model": "meigen/infinitetalk/video-to-video",
"audio": "https://v3.fal.media/files/penguin/PtiCYda53E9Dav25QmQYI_output.mp3",
"video": "https://storage.googleapis.com/falserverless/model_tests/video_models/ref_video.mp4",
"prompt": "A woman with colorful hair talking on a podcast.",
"num_frames": 145,
"resolution": "720p"
}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/b373a9938665ab03ea8f.jpg",
"source": "Self organization completed prediction",
"source_url": "https://www.sandbase.ai",
"url": "https://static.sandbase.ai/examples/b4b962b1-cb06-48d0-a0a4-6c0feb67c13b/output/28f5c266-fe95-4877-b6fa-b66237b6d2ad.mp4"
}
]