Qwen-Audio-TTS
复制成功!
Realtime-Text-to-Speech
概述
Realtime-Text-to-Speech
qwen-audio-3.0-tts-plus是面向高质量语音生成场景打造的高性能语音合成大模型。相比前一版本,模型支持更多小语种和中文方言,显著提升方言发音的正宗程度,并增强了 free-style 指令遵循能力和细粒度标签控制能力,可更准确地控制情绪、语气、角色、语速、音量和合成风格。同时,模型在噪声、混响等复杂声学条件下具备更强鲁棒性,进一步提升了音质、清晰度、分辨率和整体表现力。Plus 版本更强调合成效果和细节表现,适用于有更高音质、自然度和表现力要求的专业场景,如内容创作、有声书、影视配音、品牌声音设计和高品质语音服务。
输入
文本
输出
音频
功能
定价
- 语音合成¥1.4每万字符
速率限制
- RPM每分钟请求数180
API 参考
获取 API Key复制成功!
1234567891011121314151617181920
# coding=utf-8
import dashscope
from dashscope.audio.tts_v2 import *
# If the API Key is not configured in the environment variable, your-api-key needs to be replaced with your own API Key
# dashscope.api_key = "your-api-key"
dashscope.base_websocket_api_url='wss://dashscope.aliyuncs.com/api-ws/v1/inference'
model = "qwen-audio-3.0-tts-plus"
#Please enter the correct voice below.
voice = ""
synthesizer = SpeechSynthesizer(model=model, voice=voice)
audio = synthesizer.call("How is the weather today?")
with open('output.mp3', 'wb') as f:
f.write(audio)