Skip to main content

Task

Speech to text models

Transcription endpoints that turn recorded audio into text. The model page shows the output format, any timing information and the billing unit.

Models
2
From
$0.00003
To
$0.05
Outputs
Text
Model types
Audio

Where to start

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

Speech to text models2 models
  • HeartMuLa Transcribe

    heartmula/transcribe/speech-to-text

    Price
    $0.05 / request
    Best for
    Speech to text
    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
  • Grok STT

    xai/grok-stt/speech-to-text

    Price
    $0.00003 / output second
    Best for
    Speech to text
    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
Uncensored
Runs with no content filter added on our side.

About this category

Explore Speech to text 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