Skip to content
ArenaPlatform

cosyvoice-v3.5-plus

alibaba/cosyvoice-v3.5-plus

Current top CosyVoice model (February 2026) and Alibaba's recommended pick for voice design; synthesizes cloned or description-designed voices with free-form instruction control across 11 languages and many Chinese dialects, with no preset voice library.

Get API KeyRead the Docs
API
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/cosyvoice-v3.5-plus",
  "input": "Make every word count.",
  "voice": "auto",
  "response_format": "mp3"
}' --output speech.mp3
Read docs
Input Price
$18.70 / 1M characters
Output Price
—
Input
Text
Output
Audio

Capabilities

Explore what cosyvoice-v3.5-plus supports, then use the API section for a request tailored to this model.

BatchCustom voice

Model Information

Product
Text-to-Speech
Release Date
Feb 27, 2026
Data Policy
Not specified
Region
China
Input
Text
Output
Audio
Provider Documentation

Playground

Try cosyvoice-v3.5-plus by Alibaba Cloud Model Studio. Requests use the selected workspace’s credits and API pricing.

cosyvoice-v3.5-plusCredits —
cosyvoice-v3.5-plus
⌘ / Ctrl + Enter to send
Sign in to run a requestAPI reference

Providers

Compare available endpoints, pricing, and context limits for cosyvoice-v3.5-plus.

ProviderContextOutputInput PriceOutput PriceEndpoint
Alibaba Cloud Model StudioNot specifiedAudio$18.70 / 1M characters—
alibaba/cosyvoice-v3.5-plus:alibaba

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max chars8000
Formatswav, mp3, opus, pcm, ulaw, alaw

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/cosyvoice-v3.5-plus",
  "input": "Make every word count.",
  "voice": "auto",
  "response_format": "mp3"
}' --output speech.mp3
Read docs
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modelalibaba/cosyvoice-v3.5-plus — Required model identifier.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max chars8000
Formatswav, mp3, opus, pcm, ulaw, alaw

Similar Models

Explore more text-to-speech and compare their capabilities.

ModelContextInput PriceOutput Price
qwen-audio-3.0-tts-flashAlibaba Cloud Model StudioNot specified$12.75 / 1M characters—
qwen-audio-3.0-tts-plusAlibaba Cloud Model StudioNot specified$17.00 / 1M characters—
cosyvoice-v3.5-flashAlibaba Cloud Model StudioNot specified$9.86 / 1M characters—
Qwen3 TTS FlashAlibaba Cloud Model StudioNot specified$8.50 / 1M characters—
Qwen3 TTS Flash RealtimeAlibaba Cloud Model StudioNot specified$11.05 / 1M characters—
cosyvoice-v3-flashAlibaba Cloud Model StudioNot specified$11.05 / 1M characters—
View All Text-to-Speech