Back to model catalog

Audio

CosyVoice

Generative speech model that converts text into natural human-like speech.

Model details

Model code

cosyvoice-v3-plus

Category

Audio

Family

CosyVoice

Capability

Speech synthesis

Modality

Text -> Audio

Release / status

2026-02-10

Snapshot

Current model code

Source region

Console

Official detail price

TTS $0.26 / 10,000 characters

TTS

$0.26 / 10,000 characters

Detail checked

Source region: International. Current highlighted entries were rechecked on July 21, 2026; long-tail entries retain their earlier official detail evidence where applicable. Final quotes still require official console confirmation for region, account route, quota, promotions, taxes, and current availability.

Buyer review

Questions to confirm before purchase

Does this exact model code support the buyer's region?
Is this for Token Plan, direct API, or both?
Does the workload need text, image, video, audio, or embeddings?
Are context length, rate limits, and quota enough for production?
Are official usage cost and ModelSmarter service fee separated?
Is there a lower-cost fallback model if usage grows?

Source note

Current highlighted model coverage was checked against the official Alibaba Cloud Model Studio model page on 2026-07-21. Existing long-tail detail summaries retain their earlier console evidence date where noted. Availability, region, account route, quota, taxes, promotions, and official terms must be confirmed before purchase.

Open official console source