How is the qwen-audio-3.0-tts-plus API billed?

qwen-audio-3.0-tts-plus is pay-as-you-go from ¥56 / M. The exact rate is listed in the pricing table on this page and billed at EasyAPI's public price, with no subscription required.

How do I call qwen-audio-3.0-tts-plus through the API?

EasyAPI exposes an OpenAI-compatible API: create an API key in the console, set base_url to https://token.easyapi.com and model to qwen/qwen-audio-3.0-tts-plus, then send requests to /v1/audio/speech. The Quick Start on this page includes cURL, Python and TypeScript examples; official OpenAI SDKs only need the base_url swapped.

Which parameters does qwen-audio-3.0-tts-plus support?

The request format is OpenAI-compatible; see the Parameters table on this page for the full list and defaults.

How do I get started with qwen-audio-3.0-tts-plus?

Sign up for EasyAPI, create an API key in the console and top up your balance to call qwen-audio-3.0-tts-plus pay-as-you-go, no subscription needed. You can also try it in the online Playground first, then copy the Quick Start example.

qwen-audio-3.0-tts-plus

Name: qwen-audio-3.0-tts-plus
Brand: Qwen
Price: 56 CNY
Availability: InStock

Audio

Qwen-Audio-3.0-TTS-Plus is a high-performance large speech synthesis model built for high-quality speech generation scenarios. Compared with the previous version, it supports more low-resource languages and Chinese dialects, notably improves the authenticity of dialect pronunciation, and strengthens free-style instruction following and fine-grained tag control, enabling more precise control over emotion, tone, character, speaking rate, volume, and synthesis style. The model is also more robust under complex acoustic conditions such as noise and reverberation, further improving audio quality, clarity, resolution, and overall expressiveness. The Plus version puts greater emphasis on synthesis quality and detail, making it suited to professional scenarios with higher demands on audio quality, naturalness, and expressiveness, such as content creation, audiobooks, film and TV dubbing, brand sound design, and high-quality voice services.

Speech synthesis

0.5660% off

元/每万字符

Input

Text

Output

Audio

Speech synthesis

Pick a character to switch voices. The text and style settings follow the character.

qwen-audio-3.0-tts-plus

Characters

Text18 charsEst. ¥0.0010.56 元/每万字符

Advanced

Speed 1.00xAudio formatStyle instruction

Preview

龙安灵心

Generated audio appears here

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token

shell

export EASYAPI_API_KEY=sk-xxxxxxxx

Make your first request

Use qwen/qwen-audio-3.0-tts-plus with the EasyAPI API:

cURL

# 默认返回 JSON（audio.url 为七牛 CDN 地址）；需要音频字节时加 -H "Accept: application/octet-stream" --output speech.mp3
curl https://token.easyapi.com/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{
  "model": "qwen/qwen-audio-3.0-tts-plus",
  "input": "你好，欢迎使用 EasyAPI 语音合成。",
  "voice": "longanlingxin",
  "aigc_propagate_id": "本次请求Request ID",
  "aigc_propagator": "阿里云UID",
  "bit_rate": 32,
  "enable_aigc_tag": false,
  "response_format": "mp3"
}'

Endpoint

Synthesize text into audio. Returns JSON by default (audio.url points to a Qiniu CDN file, plus usage and billing); send Accept: application/octet-stream for raw audio bytes.

POSThttps://token.easyapi.com/v1/audio/speech

Authorization: Bearer $EASYAPI_API_KEY
Content-Type: application/json
Model: qwen/qwen-audio-3.0-tts-plus

Synthesize the text in input into audio. JSON is returned by default (audio.url / audio.data + usage + billing); audio bytes are returned when Accept: application/octet-stream is sent. Docs

Parameters

Name	Type	Required	Default	Description
`model`	string	Yes	—	Speech model ID; currently qwen/qwen-audio-3.0-tts-plus
`aigc_propagate_id`	string	No	本次请求Request ID	AIGC隐性标识的PropagateID字段，enable_aigc_tag为true时生效
`aigc_propagator`	string	No	阿里云UID	AIGC隐性标识的ContentPropagator字段，enable_aigc_tag为true时生效
`bit_rate`	integer	No	32	音频码率(kbps)，仅format为opus时支持；范围：6 ~ 510
`enable_aigc_tag`	boolean	No	false	是否在wav/mp3/opus音频中嵌入AIGC隐性标识
`enable_ssml`	boolean	No	—	是否开启SSML功能，使用SSML文本时需设为true
`hot_fix`	object	No	—	文本热修复配置，用于自定义发音或替换待合成文本
`hot_fix.pronunciation`	array	No	—	自定义发音，按词语标注拼音纠正默认发音
`hot_fix.replace`	array	No	—	文本替换，替换后文本作为实际合成内容
`input`	string	Yes	—	待合成文本，支持SSML与LaTeX格式输入
`language_hints`	array	No	—	目标语言提示，当前仅处理数组第一个元素，建议只传一个值；可选：zh / en / fr / de / ja / ko / ru / pt / th / id / vi / es / it / ms / fil / ar / other
`pitch`	number	No	1	音调；范围：0.5 ~ 2
`response_format`	string	No	mp3	音频编码格式；可选：mp3 / pcm / wav / opus
`sample_rate`	integer	No	22050	音频采样率(Hz)；opus格式仅支持8000、12000、16000、24000、48000；可选：8000 / 12000 / 16000 / 22050 / 24000 / 44100 / 48000
`seed`	integer	No	0	随机数种子，相同seed可复现合成结果；范围：0 ~ 65535
`speed`	number	No	1	语速倍率；范围：0.5 ~ 2
`voice`	string	Yes	longanlingxin	音色，必须属于当前模型：qwen-audio-3.0-tts-plus 支持 longanlingxin（龙安灵心，女）与 longanlufeng（龙安鲁风，男）；可选：longanlingxin / longanlufeng
`volume`	integer	No	50	音量；范围：0 ~ 100
`word_timestamp_enabled`	boolean	No	false	是否开启字级别时间戳，仅流式输出模式可用
`instructions`	string	No	—	风格指令，映射到百炼 input.instruction，可控制情绪、角色、方言与语速

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

qwen-audio-3.0-tts-plus FAQ

How is the qwen-audio-3.0-tts-plus API billed?: qwen-audio-3.0-tts-plus is pay-as-you-go from ¥56 / M. The exact rate is listed in the pricing table on this page and billed at EasyAPI's public price, with no subscription required.
How do I call qwen-audio-3.0-tts-plus through the API?: EasyAPI exposes an OpenAI-compatible API: create an API key in the console, set base_url to https://token.easyapi.com and model to qwen/qwen-audio-3.0-tts-plus, then send requests to /v1/audio/speech. The Quick Start on this page includes cURL, Python and TypeScript examples; official OpenAI SDKs only need the base_url swapped.
Which parameters does qwen-audio-3.0-tts-plus support?: The request format is OpenAI-compatible; see the Parameters table on this page for the full list and defaults.
How do I get started with qwen-audio-3.0-tts-plus?: Sign up for EasyAPI, create an API key in the console and top up your balance to call qwen-audio-3.0-tts-plus pay-as-you-go, no subscription needed. You can also try it in the online Playground first, then copy the Quick Start example.

Related models

All models

qwen-audio-3.0-realtime-plus

Qwen

Qwen-Audio-3.0-Realtime-Plus是一款登顶全球权威评测的下一代实时双工语音大模型，它在全球权威第三方评测平台 Artificial Analysis Speech-to-Speech子项中取得综合排名第一。千问实时语音大模型兼顾了模型智商与双工对话节奏,在保持流畅、自然的实时交互体验的同时,语音推理能力不打折扣;并通过并行推理和全向流式等工程优化,将端到端响应时延控制在低水平,实现"又快又聪明"的对话体验。标准版更注重高质量的回复结果。

音频实时语音

60% off

Input · text

¥2¥/1M tokens

Input · audio

¥16¥/1M tokens

Output · text

¥16¥/1M tokens

Output · audio

¥60¥/1M tokens

deepseek-v4-pro-0813

DeepSeek

The DeepSeek V4 flagship, with the series' strongest deep reasoning and code generation, suited to whole-codebase analysis, multi-step automation and demanding instructions.

Text

55% off

Input price

¥1.981/ M

Output price

¥5.943/ M

Cache read

¥0.066/ M

Cache write

—

deepseek-v4.1-flash

DeepSeek

DeepSeek-V4.1-Flash is DeepSeek's current mainstay model; its official API model name is deepseek-flash. It supports a 1M context and up to 384K output, with thinking and non-thinking modes switchable by default, features image understanding, tool use, and JSON Output, and is compatible with the OpenAI and Anthropic APIs.

Text

58% off

Input price

¥0.42/ M

Output price

¥1.68/ M

Cache read

¥0.0084/ M

Cache write

—

doubao-seed-2.0-lite

ByteDance

Lightweight tier of the Seed 2.0 family tuned for low-latency agent, coding, and GUI workloads.

Text

6% off

Input price

¥0.5557/ M

Output price

¥3.334/ M

Cache read

¥0.1111/ M

Cache write

—

Input

Output

Preview

Input

Output

Get your API key

Make your first request

Endpoint

Parameters

Using third-party SDKs

qwen-audio-3.0-tts-plus FAQ

Related models

Popular comparisons for qwen-audio-3.0-tts-plus