ModelRushAudio

CosyVoice V3.5 Flash API

CosyVoice V3.5 Flash synthesizes speech from text and voice controls through the ModelRush API and returns synthesized audio. Requests run synchronously and the response carries the result. It is callable in 1 execution region, from $0.000014 per character.
Speech synthesis
Starting at
$0.000014/ character
Try it in the PlaygroundLet an agent integrate this model

Input

sync
Estimated run$0.000014Current rate: $0.000014 Per input character

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/cosyvoice-v3.5-flash
Integration status
Inputs
Text · audio
Output
Text or audio
Billing unit
Per input character
Execution mode
Synchronous. The response carries the result.
Available regions
China — Beijing
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
CosyVoice V3.5 Flash · modelrush/cosyvoice-v3.5-flashText to speechStandard$0.000014 / character

Pricing and documentation

CosyVoice V3.5 Flash API pricingAudio and speech API documentation

Related guides

Evaluating Native-Audio AI Video for Speech, Events, and Ambience

Other recommended models

Audio-to-Text

Fun ASR

Speech recognition · released in 2 regions
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