InfiniteTalk Text to Video

POST/v1/run

InfiniteTalk speaks the given text with a chosen voice and animates the portrait into a talking video.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to meigen/infinitetalk/text-to-video.

Default: meigen/infinitetalk/text-to-video

stringpromptrequired

Text prompt guiding the generation.

stringimagerequired

Input image URL (face / character).

Optional<integer>seed

Random seed for reproducibility.

Range: 0 to 2147483647

Optional<integer>num_frames

Maximum frames to generate (41–721, 25 fps); output also stops at the end of the audio.

Range: 41 to 721

Default: 145

Optional<string>resolution

Output resolution (720p costs 2x).

Allowed values: 480p, 720p

Default: 720p

stringtextrequired

Text the person speaks.

stringvoicerequired

Voice used to speak the text.

Allowed values: Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: text-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meigen/infinitetalk/text-to-video",
  "text": "Spend more time with people who make you feel alive, and less with things that drain your soul.",
  "image": "https://v3.fal.media/files/panda/HuM21CXMf0q7OO2zbvwhV_c4533aada79a495b90e50e32dc9b83a8.png",
  "voice": "Bill",
  "prompt": "An elderly man with a white beard and headphones records audio with a microphone. He appears engaged and expressive, suggesting a podcast or voiceover."
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "f3d2e8a1-7c4b-4a12-9d2e-123456789abc",
  "model": "meigen/infinitetalk/text-to-video",
  "status": "running"
}