← All models
Generates soundtracks from an uploaded image or video, with optional style and mood guidance, audio-range selection, and multiple variations.
Details
- Accepts
- text
Pricing
- Price
- 12.5 cr / request
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| prompt | — | Optional description of the desired soundtrack style and mood. |
| image_id | — | Image ID returned by /files/upload with purpose='soundtrack'. Provide exactly one of image_id or video_id. |
| video_id | — | Video ID returned by /files/upload with purpose='soundtrack'. Provide exactly one of image_id or video_id. |
| audio_end | — | End time of the soundtrack audio in milliseconds. If both audio_start and audio_end are specified, generation uses those times. If audio_end exceeds the song duration, generation stops at the end of the song. The soundtrack audio segment must be at least 3 seconds long, and a 1-second fade-out is ad… |
| audio_start | — | Start time of the soundtrack audio in milliseconds. If only audio_start is specified, generation starts there and continues for the video duration, stopping at the end of the song if the remaining audio is shorter. The soundtrack audio segment must be at least 3 seconds long, and a 1-second fade-in … |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. |
Output
| Field | Type | Description |
|---|---|---|
| audio | — | The generated audio file. |
| song_id | — | Reusable identifier for this audio. Pass it to endpoints that accept song_id. |
| duration | — | Duration of the generated audio in milliseconds, when available. |
| lyrics_sections | — | Timed lyric sections for the generated audio, when available. |