Generate a music track or a sound effect from a prompt
Music and sound-effect generation on one endpoint, billed per track or per clip in USDC. Priced before the call runs, with no subscription and no API key.
What it does
Music is a style prompt, optional lyrics or an instrumental flag, and a model; sound effects are a short description on a separate endpoint. Each is one request billed per finished track or clip, and the result is returned on a durable URL.
Music runs to several minutes and a sound effect to a short clip — each model's ceiling is on its row. Both are asynchronous where the model is: the call returns a job when generation takes longer than a request can wait.
The call
One endpoint, priced in dollars before it runs and settled in USDC. No API key and no account — the request pays for itself.
POST /api/v1/audio/generations
Host: blockrun.aiWhat it costs
Why per call
No seat, no minimum, no contract per vendor. Each request is quoted in dollars before it runs and settles on-chain, so an agent can pay for its own work without a human holding a credit card. How the payment works →
Related tools
Questions
Music and sound effects on one page?
Yes — both are generated audio on the same endpoint, and each has one model behind it today.
Can I supply my own lyrics?
Yes. The music model accepts lyrics as well as a style prompt, or will produce an instrumental.
How is it billed?
Per finished track or clip, quoted in dollars before generation begins.
How long can output be?
Each model has its own ceiling — the music model runs to several minutes and the sound-effect model to a short clip.