.mp3 that fits the picture.
The connection between them is plain JSON: the vision model returns a style and lyrics, and the music API takes exactly those two fields.
The plan
1
Read the image
POST /v1/chat/completions with a vision model and the image, asking for JSON with a style prompt and lyrics.2
Generate the song
POST /v1/audio/generations with prompt set to the style and lyrics_prompt set to the lyrics.3
Poll and download
Poll
GET /v1/audio/generations/{id} until completed, then download audio[0].url.Full script
Notes
- Use a vision-capable model for step 1.
deepshi-3.0reads images and returns JSON. Send the image as a URL or a base64data:URI. minimax-music-v2is a vocal model, so it needslyrics_prompt. Asking the vision model to write the lyrics keeps the whole chain in one pass.- Cost: the chat call reports its cost inline in
usage.cost. The song is billed once on completion; see music pricing.
Next steps
Music generation
All music parameters, models, and pricing.
Animate an image
Chain image generation into a video clip.