ModelRushAudio
Qwen3 ASR Flash Filetrans API
Qwen3 ASR Flash Filetrans 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 $0.000036 per second.Speech recognition
Current rate
$0.000036/ second
Output preview

default5s
Model information
Best for
Product featuresAutomated workflowsAgent tools
Current customer pricing
Each row identifies the Operation, Region, price variant, and immutable price version used for execution.| Model | Capability | Execution Region | Price variant | Customer price |
|---|---|---|---|---|
| Qwen3 ASR Flash Filetrans · modelrush/qwen3-asr-flash-filetrans | Audio transcription | cn-beijing | Standard | $0.000036 / second |
| Qwen3 ASR Flash Filetrans · modelrush/qwen3-asr-flash-filetrans | Audio transcription | sg-singapore | Standard | $0.000039 / second |
Pricing and documentation
Other recommended models

Text-to-Audio
Cosyvoice V3.5 Flash
Speech synthesis · released in 1 regionStarting pricePricing pending

Text-to-Audio
Cosyvoice V3.5 Plus
Speech synthesis · released in 1 regionStarting pricePricing pending

ModelRushOne integration, intelligent routing, transparent billing. Model infrastructure for developers and agents.© 2026 ModelRushAll systems operational