BaiLian

Cosyvoice V3.5 Plus

AlibabaToken-based
Alias:cosyvoice-v3.5-plus
Create API Key

Compare cosyvoice-v3.5-plus API pricing, supported endpoints, capabilities and access options on Modelsell.

tts语音合成streaming声音复刻声音设计指令控制
Starting price
Input / Output · 1M
Context
—
Maximum input window
Modalities
→
Released
Feb 2026

Pricing by Supplier

Alibaba
阿里巴巴百炼官方
Input$22.0588/ 1M
Output$0/ 1M

Capabilities / Supported modalities

Streaming
Input
Output

Provider & data privacy

Provider
Unknown
Tokenizer
BPE (vendor-specific)
License
Provider-specificUnknown
Data retention64 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·Cosyvoice V3.5 Plus

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About Cosyvoice V3.5 Plus

用同一种声音讲述不同内容

CosyVoice-v3.5-Plus 侧重声音复刻、声音设计后的合成表现,适合品牌旁白、有声读物、展览导览和多语言内容。它将待朗读文字转为音频,在保留说话人音色特点的同时,通过自由风格指令调整表达,让同一音色用于平静讲解、热情欢迎或带有角色感的叙述。

模型支持中文、英文、德文、法文、俄文、日文、韩文、葡萄牙文、泰文、印尼文和越南文,可用于跨语言的语音内容制作。需要多语言版本时,应分别准备准确的正文,保留一致的术语与人名写法,再试听不同语言的发音和节奏;合成服务本身不负责翻译校对。

先准备音色,再安排表演

v3.5 不提供系统预置音色。先通过声音复刻或声音设计创建适配目标模型的 voice ID,再用这个 ID 合成。复刻适合已有明确声音素材的项目,设计适合从文字描述创建新的声音方向。创建音色和生成最终配音是两个步骤,不能把音色描述直接当成 voice ID。

复刻与设计音色都支持自然语言指令,可以写清语气、语速和停顿要求。试听时先固定音色,只改变一两个表达维度;长篇内容按段落处理,检查段间衔接。模型支持流式合成,应用可逐段接收音频,或在完整合成后保存文件。

北京地域基准价为 1.5 元/万计费字符,输出音频不另收费。汉字通常计 2 个字符,SSML 标签不计入,按返回的计费字符数结算。美元基准按 1 美元 = 6.8 元换算,最终费用应用账户分组倍率。

Use cases and prompting

展览导览制作

先创建适配 cosyvoice-v3.5-plus 的复刻或设计音色,取得 voice ID。

正文:“眼前这件陶器距今已有两千多年。请注意器身上的纹样,它记录着当时人们对生活的观察。”

instruction:“温和沉稳,像面对观众讲解,语速稍慢,重点词自然强调。”

可以直接选择常见的系统音色吗?

v3.5 需要自建复刻或设计音色,不能直接沿用其他版本的系统音色。

自建音色无法使用时检查什么?

确认 voice ID 创建成功、适配目标模型,并检查调用账号与地域是否一致。

API access

API documentation

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Rate limits

SupplierRPMTPMRPD
AlibabaUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about cosyvoice-v3.5-plus

What is cosyvoice-v3.5-plus?

Compare cosyvoice-v3.5-plus API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call cosyvoice-v3.5-plus?

Create an API key with access to cosyvoice-v3.5-plus, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is cosyvoice-v3.5-plus priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

How should I evaluate cosyvoice-v3.5-plus for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.