ModelRushAudio
Qwen3 TTS VC Realtime 2026-01-15 API
Qwen3 TTS VC Realtime 2026-01-15 runs realtime sessions from streamed audio and text through the ModelRush API and returns a streamed session. Requests run synchronously and the response carries the result. It is callable in 2 execution regions, from $0.000015 per character.Speech synthesis
Current rate
$0.000015/ character
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 TTS VC Realtime 2026-01-15 · modelrush/qwen3-tts-vc-realtime-2026-01-15 | Realtime | cn-beijing | Standard | $0.000017 / character |
| Qwen3 TTS VC Realtime 2026-01-15 · modelrush/qwen3-tts-vc-realtime-2026-01-15 | Realtime | sg-singapore | Standard | $0.000015 / character |
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