Skip to main content

daVinci-MagiHuman API

sand-ai/davinci-magihuman/text-to-video

daVinci-MagiHuman text-to-video turns a written prompt into a 5 to 10 second clip with a voice: put the spoken line in quotes and the model speaks it. 256p, 720p or 1080p, 16:9 or 9:16, with an optional audio file.

From $0.024/s
Run model

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Output5s
    balcony-goodbye-line

    1080p at 16:9, five seconds: it came back about 1904 x 1088 at 25 fps with sound, after about 3 min 53 s. The line is in quotes with how it is said, and our transcription of the soundtrack matched it word for word: "You really thought I'd leave without saying goodbye?"

    • 11
    • 1080p
    • 16:9
  • Output5s
    rainy-street-selfie

    720p at 9:16, five seconds: about 726 x 1270, after about a minute. The man laughs and says his line, and the transcription matched: "Okay, I'm lost, but honestly? Best night of the trip." The prompt says "looks straight into the camera"; in an extra run, asking for a selfie with a phone put a phone in the frame.

    • 33
    • 720p
    • 9:16

This example starts at $0.024 per output second. The Playground updates the estimate when you change the settings.