AxForge offering
When this offering is available: Full songs (vocals, arrangement and mix) from your lyrics and a one-line musical brief, through the /v1/audio/music endpoint on hardware AxForge owns in Stockholm. Up to five minutes per track, 32 kHz 16-bit stereo WAV, zero prompt retention.
Check the console for current access, prices and availability.
Why AxForge
| Songs, not loops | Full songs up to 5 minutes: vocals and arrangement generated from your lyrics, structure marked with [verse] and [chorus] tags so choruses come back as the hook. Omit the lyrics and you get an instrumental. |
|---|---|
| Commercial use, two honest obligations | Build paid products on this endpoint. The model's licence asks that your product name MiniMax-Music3 and label the audio as machine-generated. A line in the UI or the credits is enough. |
| Zero prompt retention | Prompts, lyrics and generated audio are processed in memory in Stockholm, Sweden. Not logged, not retained, never used for training. |
Specifications
| Model | MiniMax-Music3, full-song music generation: vocals + arrangement from lyrics |
|---|---|
| API model name | minimax-music3 |
| Endpoint | POST /v1/audio/music |
| Output | Tracks up to 5 minutes, 32 kHz 16-bit stereo WAV, as base64 in data[].b64_json |
| Parameters | prompt (genre, BPM, instrumentation), lyrics, duration_s (up to 180, about 4 s to make each second), seed |
| Licence | MiniMax model licence: commercial use permitted; name the model and disclose machine-generated audio |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Region | Stockholm, Sweden (eu-se-1) |
| Price | €0.04 / 10 seconds (launch pricing) |
MiniMax Music 3 catalogue reference: specifications and requirements. List prices in EUR.
How it works
| 1 | Confirm this offering is available in the console before following the API setup steps below; otherwise add a public request. A request does not activate an endpoint. |
|---|---|
| 2 | Sign in to AxForge. Your API key is created in the console. |
| 3 | Set base_url to https://api.axforge.ai/v1. |
| 4 | POST /v1/audio/music with model minimax-music3, a musical prompt, optional [verse]/[chorus] lyrics and duration_s. |
| 5 | Run it as a background job with a generous timeout, since a song takes minutes, not milliseconds. |
| 6 | Decode data[0].b64_json to a WAV and drop it on the timeline. |
FAQ
Full songs up to 5 minutes: vocals and arrangement generated from your lyrics, with the style set by a musical description (genre, BPM, instrumentation, mood). Omit the lyrics and you get an instrumental. Output is 32 kHz 16-bit stereo WAV.
You mark the song's structure inside the lyrics field: [verse] and [chorus] tags divide your lines into sections, and the model writes the melody and arrangement around the structure you give it, so choruses come back as the hook.
Yes. Omit the lyrics field and describe what you want in the prompt (for example ambient piano, 60 BPM, warm tape texture) and the track comes back fully instrumental.
Track generation runs minutes-scale. Treat it as a background job: call the endpoint from a worker with a generous timeout, not inside a blocking user-facing request.
Yes. Build paid products on this endpoint. The licence asks two things of your product: name MiniMax-Music3 and label the audio as machine-generated. Rights in machine-generated music vary by jurisdiction, so run your specific use past your counsel.
When available, check current pricing in the console. €0.04 per 10 seconds of music (launch pricing). Prompts, lyrics and generated audio are processed in memory in Sweden, never persisted or used for training; only request metadata is kept for billing and operations.