Text to speech

import requests
import json

url = "https://api.siliconflow.cn/v1/uploads/audio/voice"
headers = {
    "Authorization": "Bearer your-api-key", # 从 https://cloud.siliconflow.cn/account/ak 获取
    "Content-Type": "application/json"
}
data = {
    "model": "FunAudioLLM/CosyVoice2-0.5B", # model name
    "customName": "your-voice-name", # user-predefined voices name
    "audio": "data:audio/mpeg;base64,SUQzBAAAAAAAIlRTU0UAAAAOAAADTGF2ZjYxLjcuMTAwAAAAAAAAAAAAAAD/40DAAAAAAAAAAAAASW5mbwAAAA8AAAAWAAAJywAfHx8fKioqKio1NTU1Pz8/Pz9KSkpKVVVVVVVfX19fampqamp1dXV1f39/f3+KioqKlZWVlZWfn5+fn6qqqqq1tbW1tb+/v7/KysrKytXV1dXf39/f3+rq6ur19fX19f////", # 参考音频的 base64 编码
    "text": "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始" # 参考音频的文字内容
}

response = requests.post(url, headers=headers, data=json.dumps(data))

# 打印响应状态码和响应内容
print(response.status_code)
print(response.json())  # 如果响应是 JSON 格式

{'uri': 'speech:your-voice-name:cm04pf7az00061413w7kz5qxs:mjtkgbyuunvtybnsvbxd'}

import requests

url = "https://api.siliconflow.cn/v1/uploads/audio/voice"
headers = {
    "Authorization": "Bearer your-api-key" # 从 https://cloud.siliconflow.cn/account/ak 获取
}
files = {
    "file": open("/Users/senseb/Downloads/fish_audio-Alex.mp3", "rb") # 参考音频文件
}
data = {
    "model": "FunAudioLLM/CosyVoice2-0.5B", # 模型名称
    "customName": "your-voice-name", # 参考音频名称
    "text": "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始" # 参考音频的文字内容
}

response = requests.post(url, headers=headers, files=files, data=data)

print(response.status_code)
print(response.json())  

{'uri': 'speech:your-voice-name:cm04pf7az00061413w7kz5qxs:mjtkgbyuunvtybnsvbxd'}

import requests
url = "https://api.siliconflow.cn/v1/audio/voice/list"

headers = {
    "Authorization": "Bearer your-api-key" # 从https://cloud.siliconflow.cn/account/ak获取
}
response = requests.get(url, headers=headers)

print(response.status_code)
print(response.json()) 

{'uri': 'speech:your-voice-name:cm04pf7az00061413w7kz5qxs:mjtkgbyuunvtybnsvbxd'}

import requests

url = "https://api.siliconflow.cn/v1/audio/voice/deletions"
headers = {
    "Authorization": "Bearer your-api-key",
    "Content-Type": "application/json"
}
payload = {
    "uri": "speech:your-voice-name:cm02pf7az00061413w7kz5qxs:mttkgbyuunvtybnsvbxd"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.status_code)
print(response.text) 

from pathlib import Path
from openai import OpenAI

speech_file_path = Path(__file__).parent / "siliconcloud-generated-speech.mp3"

client = OpenAI(
    api_key="您的 APIKEY", # 从 https://cloud.siliconflow.cn/account/ak 获取
    base_url="https://api.siliconflow.cn/v1"
)

with client.audio.speech.with_streaming_response.create(
  model="FunAudioLLM/CosyVoice2-0.5B", # 支持 fishaudio / GPT-SoVITS / CosyVoice2-0.5B 系列模型
  voice="FunAudioLLM/CosyVoice2-0.5B:alex", # 系统预置音色
  # 用户输入信息
  input="你能用高兴的情感说吗？<|endofprompt|>今天真是太开心了，马上要放假了！I'm so happy, Spring Festival is coming!",
  response_format="mp3" # 支持 mp3, wav, pcm, opus 格式
) as response:
    response.stream_to_file(speech_file_path)

from pathlib import Path
from openai import OpenAI

speech_file_path = Path(__file__).parent / "siliconcloud-generated-speech.mp3"

client = OpenAI(
    api_key="您的 APIKEY", # 从 https://cloud.siliconflow.cn/account/ak 获取
    base_url="https://api.siliconflow.cn/v1"
)

with client.audio.speech.with_streaming_response.create(
  model="FunAudioLLM/CosyVoice2-0.5B", # 支持 fishaudio / GPT-SoVITS / CosyVoice2-0.5B 系列模型
  voice="speech:your-voice-name:cm02pf7az00061413w7kz5qxs:mttkgbyuunvtybnsvbxd", # 用户上传音色名称，参考
  # 用户输入信息
  input=" 请问你能模仿粤语的口音吗？< |endofprompt| >多保重，早休息。",
  response_format="mp3"
) as response:
    response.stream_to_file(speech_file_path)

from pathlib import Path
from openai import OpenAI
client = OpenAI()

speech_file_path = Path(__file__).parent / "siliconcloud-generated-speech.mp3"

client = OpenAI(
    api_key="您的 APIKEY", # 从 https://cloud.siliconflow.cn/account/ak 获取
    base_url="https://api.siliconflow.cn/v1"
)

with client.audio.speech.with_streaming_response.create(
  model="FunAudioLLM/CosyVoice2-0.5B", 
  voice="", # 此处传入空值，表示使用动态音色
  # 用户输入信息
  input="  [laughter]有时候，看着小孩子们的天真行为[laughter]，我们总会会心一笑。",
  response_format="mp3",
  extra_body={"references":[
        {
            "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Alex.mp3", # 参考音频 url。也支持 base64 格式
            "text": "在一无所知中, 梦里的一天结束了，一个新的轮回便会开始", # 参考音频的文字内容
        }
    ]}
) as response:
    response.stream_to_file(speech_file_path)

# -*- coding: utf-8 -*-
import requests
import json

url = "https://api.siliconflow.cn/v1/audio/speech"
token = "Your-api-key"

request_data = {
                "model": "fnlp/MOSS-TTSD-v0.5",
                "stream": True,
                "input": "[S1]Hello, how are you today?[S2]I'm doing great, thanks for asking![S1]That's wonderful to hear.",
                "references": [
                    {
                        "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Charles.mp3",
                        "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦",
                    },
                    {
                        "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Claire.mp3",
                        "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦"
                    }
                    ],
                "max_tokens": 1600,
                "response_format": "mp3",
                "speed": 1,
                "gain": 0
                }
headers = {'Content-Type': 'application/json', 'Authorization': "Bearer " + token}
try:
    res = requests.post(url=url, data=json.dumps(request_data), headers=headers)
    if res.status_code != 200:
        print(res.text)
    with open('./test.mp3', 'wb') as file:
        file.write(res.content)
except Exception as e:
    print(request_data)
    print(e)