mirage-api/avatar-x/reference-to-video
Publicly fetchable HTTPS URL of the driving audio; no cookies or authorization headers. Supports MP3, PCM WAV or AIFF, AAC or ALAC, Opus or Vorbis, and FLAC audio from 3 to 180 seconds and up to 64 MiB, with one mono or stereo stream sampled from 8 to 48 kHz. The generated video follows this audio.
Run the model to see the result here.