Try MiniMax FastH3 V2 from Fastvideo →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Video GenerationActive

memo

bywiro

Memory-Guided Diffusion for Expressive Talking Video Generation. Produces a video by applying the audio file to the input image. (Image2Video)

Talking HeadImage To VideoLip Sync
Model ID
memo
Provider
wiro
Updated
1784810323
wiro playground—wiro/memo
Reset to defaults
0 / 1
Maximum 1 image allowed

Choose an image that will re-generate

0 / 1
Maximum 1 audio allowed

You can upload audio files in MP3, WAV, OGG, M4A or WebM format.

Sample outputs
Before comparison sampleBeforeAfterUse left and right arrow keys to compare the samples.
Updated 1784810323

Memory-Guided Diffusion for Expressive Talking Video Generation. Produces a video by applying the audio file to the input image. (Image2Video - Talking head)

API quick start

Run memo with a single API call.

POST https://api.wiro.ai/v1/Run/wiro/memo
{
  "inputImage": "https://your-cdn.com/input.png",
  "inputAudio": "https://your-cdn.com/input.mp3",
  "resolution": 512,
  "fps": 30
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/wiro/memo" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "inputImage": "https://your-cdn.com/input.png",
  "inputAudio": "https://your-cdn.com/input.mp3",
  "resolution": 512,
  "fps": 30
}
JSON
View full API docs