利用TTS，让你的AI Agent发声！

- 用户 -> Agent -> 文本回答

- 用户 -> Agent -> 文本回答
           |
           v
        TTS服务 -> MSTTS -> 语音回答

- 用户 -> Agent -> 文本回答
           |
           v (异步)
        TTS服务 -> MSTTS -> 语音回答

curl -H "Authorization: Bearer "$(gcloud auth print-access-token) -H "x-goog-user-project: <var>PROJECT_ID</var>" -H "Content-Type: application/json; charset=utf-8" --data "{
  'input':{
    'text':'I\'ve added the event to your calendar.'
  },
  'voice':{
    'languageCode':'en-gb',
    'name':'en-GB-Standard-A',
    'ssmlGender':'FEMALE'
  },
  'audioConfig':{
    'audioEncoding':'MP3'
  }
}" "https://texttospeech.googleapis.com/v1/text:synthesize"

@app.post("/chat")
def chat(query: str, background_tasks: BackgroundTasks):
    master = Master()
    msg = master.run(query)
    unique_id = str(uuid.uuid4())
    background_tasks.add_task(master.background_voice_synthesis, msg, unique_id)
    return {"msg": msg, "id": unique_id}

def background_voice_synthesis(self, text: str, uid: str):
    # 无返回值，只是触发语音合成
    asyncio.run(self.get_voice(text, uid))

# text 要转换为语音的文本
    async def get_voice(self, text: str, uid: str):
        print("text2speech", text)
        print("uid", uid)
        print("当前Edge大师应该的语气是：", self.emotion)
        # 默认 grpc 会报 503 错误，必须 rest 请求
        client = texttospeech.TextToSpeechClient(transport="rest")
        input_text = texttospeech.SynthesisInput(text="fsfsdfsd")
        print("input_text=", input_text)
        # Note: the voice can also be specified by name.
        # Names of voices can be retrieved with client.list_voices().
        voice = texttospeech.VoiceSelectionParams(
            language_code="en-US",
            name="en-US-Studio-O",
        )

        audio_config = texttospeech.AudioConfig(
            audio_encoding=texttospeech.AudioEncoding.LINEAR16,
            speaking_rate=1
        )

        response = client.synthesize_speech(
            request={"input": input_text, "voice": voice, "audio_config": audio_config}
        )
        print("respnotallow=", response)
        # The response's audio_content is binary.
        with open("output.mp3", "wb") as out:
            out.write(response.audio_content)
            print('Audio content written to file "output.mp3"')

import os

from dotenv import load_dotenv

load_dotenv("qwen.env")

import sys
from dashscope.audio.tts import SpeechSynthesizer

result = SpeechSynthesizer.call(model='sambert-zhichu-v1',
                                text='今天天气怎么样',
                                sample_rate=48000)
if result.get_audio_data() is not None:
    with open('output.wav', 'wb') as f:
        f.write(result.get_audio_data())
    print('SUCCESS: get audio data: %dbytes in output.wav' %
          (sys.getsizeof(result.get_audio_data())))
else:
    print('ERROR: response is %s' % (result.get_response()))

# Installation instructions for pyaudio:
# APPLE Mac OS X
#   brew install portaudio 
#   pip install pyaudio
# Debian/Ubuntu
#   sudo apt-get install python-pyaudio python3-pyaudio
#   or
#   pip install pyaudio
# CentOS
#   sudo yum install -y portaudio portaudio-devel && pip install pyaudio
# Microsoft Windows
#   python -m pip install pyaudio

import dashscope
import sys
import pyaudio
from dashscope.api_entities.dashscope_response import SpeechSynthesisResponse
from dashscope.audio.tts import ResultCallback, SpeechSynthesizer, SpeechSynthesisResult

dashscope.api_key='sk-xxx'

class Callback(ResultCallback):
    _player = None
    _stream = None

    def on_open(self):
        print('Speech synthesizer is opened.')
        self._player = pyaudio.PyAudio()
        self._stream = self._player.open(
            format=pyaudio.paInt16,
            channels=1,
            rate=48000,
            output=True)

    def on_complete(self):
        print('Speech synthesizer is completed.')

    def on_error(self, response: SpeechSynthesisResponse):
        print('Speech synthesizer failed, response is %s' % (str(response)))

    def on_close(self):
        print('Speech synthesizer is closed.')
        self._stream.stop_stream()
        self._stream.close()
        self._player.terminate()

    def on_event(self, result: SpeechSynthesisResult):
        if result.get_audio_frame() is not None:
            print('audio result length:', sys.getsizeof(result.get_audio_frame()))
            self._stream.write(result.get_audio_frame())

        if result.get_timestamp() is not None:
            print('timestamp result:', str(result.get_timestamp()))

callback = Callback()
SpeechSynthesizer.call(model='sambert-zhichu-v1',
                       text='你是睿智的JavaEdge',
                       sample_rate=48000,
                       format='pcm',
                       callback=callback)