聲音設計

import base64
import os

import dashscope
import requests
from dashscope.audio.tts_v2 import AudioFormat, SpeechSynthesizer

api_key = os.environ["DASHSCOPE_API_KEY"]
workspace_id = "YOUR_WORKSPACE_ID"
target_model = "qwen-audio-3.1-tts-flash"

# 创建音色，并将返回的预览音频保存到本地。
response = requests.post(
    f"https://{workspace_id}.cn-beijing.maas.aliyuncs.com/api/v1/services/audio/tts/customization",
    headers={"Authorization": f"Bearer {api_key}"},
    json={
        "model": "voice-enrollment",
        "input": {
            "action": "create_voice",
            "target_model": target_model,
            "voice_prompt": "沉稳的中年男性播音员，音色低沉浑厚，富有磁性，语速平稳，吐字清晰，适合用于新闻播报或纪录片解说。",
            "preview_text": "各位听众朋友，大家好，欢迎收听晚间新闻。",
            "prefix": "announcer",
            "language_hints": ["zh"],
        },
        "parameters": {"sample_rate": 24000, "response_format": "wav"},
    },
    timeout=120,
)
response.raise_for_status()
output = response.json()["output"]
voice_id = output["voice_id"]
print(f"voice_id: {voice_id}")
with open("preview.wav", "wb") as f:
    f.write(base64.b64decode(output["preview_audio"]["data"]))

# 使用创建音色时指定的模型和返回的音色 ID 合成语音。
dashscope.api_key = api_key
dashscope.base_websocket_api_url = (
    f"wss://{workspace_id}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference"
)
synthesizer = SpeechSynthesizer(
    model=target_model,
    voice=voice_id,
    format=AudioFormat.WAV_24000HZ_MONO_16BIT,
)
audio = synthesizer.call("今天天气晴朗，适合外出散步。祝你度过愉快的一天。")
with open("output.wav", "wb") as f:
    f.write(audio)