Skip to main content

Task

Text to audio models

Endpoints that turn a written description into a finished audio clip, such as a scene with dialogue, music, ambience and sound effects. Each model page shows how it is billed.

Models
5
From
$0.072
To
$0.36
Outputs
Audio

Where to start

A few families worth opening first. Every model and price in this category is listed in the table below.

Text to audio models5 models
  • Suno v6 Mini

    suno/v6-mini/text-to-audio

    Price
    $0.072 / request
    Best for
    Text to audio
    Content limits
    Filtered — This model refuses requests beyond its own limits outright. Measured, not assumed — models we have not measured carry no label at all.
    View details
  • Suno v6 Wild

    suno/v6-wild/text-to-audio

    Price
    $0.072 / request
    Best for
    Text to audio
    Content limits
    Filtered — This model refuses requests beyond its own limits outright. Measured, not assumed — models we have not measured carry no label at all.
    View details
  • Suno v6

    suno/v6/text-to-audio

    Price
    $0.072 / request
    Best for
    Text to audio
    Content limits
    Filtered — This model refuses requests beyond its own limits outright. Measured, not assumed — models we have not measured carry no label at all.
    View details
  • Seed Audio 1.0

    bytedance/seed-audio-1.0/text-to-audio

    Price
    $0.36 / request
    Best for
    Text to audio
    Content limits
    Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.
    View details
  • MiniMax Music 3.0

    minimax/music-3.0/text-to-audio

    Price
    $0.18 / request
    Best for
    Text to audio
    Content limits
    Filtered — This model refuses requests beyond its own limits outright. Measured, not assumed — models we have not measured carry no label at all.
    View details
Uncensored
Runs with no content filter added on our side.
Filtered
Requests beyond the model's own limits are refused outright.

About this category

Explore Text to audio models and compare their inputs, current pricing and capabilities. SpicyAPI adds no content scanning; capabilities depend on the selected model. Submit media tasks with createTask and receive results through recordInfo polling or callbacks. Usage is billed in each model’s own unit. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.

Keep looking