ModelRushAudio

Fun ASR API

Fun ASR transcribes audio from audio files or URLs through the ModelRush API and returns a text transcript. Requests run synchronously and the response carries the result. It is callable in 2 execution regions, from $0.000039 per second.
Speech recognition
Starting at
$0.000039/ second
Try it in the PlaygroundLet an agent integrate this model

Input

sync
Estimated run$0.000195Current rate: $0.000039 Per second of output

Output preview

This is a model capability preview. Sign in to submit a live request and inspect the generated result here.
default5s

Model information

Model ID
modelrush/fun-asr
Integration status
Inputs
Text · audio
Output
Text or audio
Billing unit
Per second of output
Execution mode
Synchronous. The response carries the result.
Available regions
China — BeijingSingapore
Last updated
Oct 15, 2026

Best for

Product featuresAutomated workflowsAgent tools

Current customer pricing

For each Operation and price variant, the highest regional customer price is shown.
ModelCapabilityPrice variantCustomer price
Fun ASR · modelrush/fun-asrAudio transcriptionStandard$0.000039 / second

Pricing and documentation

Fun ASR API pricingAudio and speech API documentation

Other recommended models

Text-to-Audio

Cosyvoice V3.5 Flash

Speech synthesis · released in 1 region
Starting pricePricing pending
Tools

Qwen Voice Enrollment

Voice cloning · released in 2 regions
Starting pricePricing pending
Tools

Voice Enrollment

Voice cloning · released in 2 regions
Starting pricePricing pending