CosyVoice 3.5 Plus

Alibaba / Qwen
Model overview

cosyvoice-v3.5-plus

Alibaba Cloud's current high-quality speech synthesis and voice-control model.

speechtext to speechaudiovoice assistantcreative generationenterprise access
Representative version

cosyvoice-v3.5-plus

CompanyAlibaba / Qwen
Release2026-03-02
Release typeModel release
ParametersNot disclosed
ArchitectureNot disclosed
ContextNot disclosed
Input modalitiestext / audio
Output modalitiesaudio
Tool use / function callingNot disclosed
Structured output / reasoningNot disclosed
Vision / audio / videoConfirmed: Audio
Open weights / LicenseNo open weights / license not applicable
alibaba-qwen-cosyvoice-3-5-plus-current · License not applicable
Vendor APIAvailable
Alibaba Cloud Model Studio model catalogalibaba-qwen-cosyvoice-3-5-plus-current · 2026-03-02
OpenRouterNot separately listed on OpenRouter
PricingOfficial pricing page
BenchmarkNo reliable public source
Public signalsNo reliable public source
Use casesText-to-speech / Voice cloning / Voice assistants / voice assistant
Claim evidenceRelease / model specs / weightsAlibaba Cloud Model Studio model catalogcosyvoice-v3.5-plus · 2026-03-02
OpenRouter

Pricing / context / availability

OpenRouterNot separately listed on OpenRouter
OpenRouter listingNot separately listed in the current OpenRouter public list
Mapped versioncosyvoice-v3.5-plus
alibaba-qwen-cosyvoice-3-5-plus-current
PricingOfficial pricing page
ContextNot disclosed
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Evidence gaps

Public display boundary

Parameter scale not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo public model-card activity countersNo linkable real reviewSpeed/latency not disclosed