Non-real-time speech synthesis

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

text = "Today is a wonderful day to build something people love!"
# To use the SpeechSynthesizer interface: dashscope.audio.qwen_tts.SpeechSynthesizer.call(...)
response = dashscope.MultiModalConversation.call(
  # Replace the model with qwen3-tts-instruct-flash to use instruction control.
  model="qwen3-tts-flash",
  # If you have not configured an environment variable, replace the following line with your API key: api_key = "sk-xxx"
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  text=text,
  voice="Cherry",
  language_type="English", # We recommend that this matches the text language to ensure correct pronunciation and natural intonation.
  # To use instruction control, uncomment the following lines and replace the model with qwen3-tts-instruct-flash.
  # instructions='Speak quickly with a noticeable rising intonation, suitable for introducing fashion products.',
  # optimize_instructions=True,
  stream=False
)
print(response)

# coding=utf-8
#
# 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 os
import dashscope
import pyaudio
import time
import base64
import numpy as np

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

p = pyaudio.PyAudio()
# Create an audio stream
stream = p.open(format=pyaudio.paInt16,
        channels=1,
        rate=24000,
        output=True)


text = "Today is a wonderful day to build something people love!"
response = dashscope.MultiModalConversation.call(
  # If you have not configured an environment variable, replace the following line with your API key: api_key = "sk-xxx"
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  # Replace the model with qwen3-tts-instruct-flash to use instruction control.
  model="qwen3-tts-flash",
  text=text,
  voice="Cherry",
  language_type="English", # We recommend that this matches the text language to ensure correct pronunciation and natural intonation.
  # To use instruction control, uncomment the following lines and replace the model with qwen3-tts-instruct-flash.
  # instructions='Speak quickly with a noticeable rising intonation, suitable for introducing fashion products.',
  # optimize_instructions=True,
  stream=True
)

for chunk in response:
  if chunk.output is not None:
      audio = chunk.output.audio
      if audio.data is not None:
          wav_bytes = base64.b64decode(audio.data)
          audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
          # Play the audio data directly
          stream.write(audio_np.tobytes())
      if chunk.output.finish_reason == "stop":
          print("finish at: {} ", chunk.output.audio.expires_at)
time.sleep(0.8)
# Clean up resources
stream.stop_stream()
stream.close()
p.terminate()

import os
import requests
import base64
import pathlib
import dashscope

# ======= Constant configuration =======
DEFAULT_TARGET_MODEL = "qwen3-tts-vc-2026-01-22"  # Use the same model for voice cloning and speech synthesis
DEFAULT_PREFERRED_NAME = "guanyu"
DEFAULT_AUDIO_MIME_TYPE = "audio/mpeg"
VOICE_FILE_PATH = "voice.mp3"  # Relative path to the local audio file used for voice cloning


def create_voice(file_path: str,
                 target_model: str = DEFAULT_TARGET_MODEL,
                 preferred_name: str = DEFAULT_PREFERRED_NAME,
                 audio_mime_type: str = DEFAULT_AUDIO_MIME_TYPE) -> str:
  """
  Create a voice and return the voice parameter.
  """
  # If you haven't configured an environment variable, replace the following line with: api_key = "sk-xxx"
  api_key = os.getenv("DASHSCOPE_API_KEY")

  file_path_obj = pathlib.Path(file_path)
  if not file_path_obj.exists():
    raise FileNotFoundError(f"Audio file does not exist: {file_path}")

  base64_str = base64.b64encode(file_path_obj.read_bytes()).decode()
  data_uri = f"data:{audio_mime_type};base64,{base64_str}"

  url = "https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization"
  payload = {
    "model": "qwen-voice-enrollment", # Do not change this value
    "input": {
      "action": "create",
      "target_model": target_model,
      "preferred_name": preferred_name,
      "audio": {"data": data_uri}
    }
  }
  headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
  }

  resp = requests.post(url, json=payload, headers=headers)
  if resp.status_code != 200:
    raise RuntimeError(f"Failed to create voice: {resp.status_code}, {resp.text}")

  try:
    return resp.json()["output"]["voice"]
  except (KeyError, ValueError) as e:
    raise RuntimeError(f"Failed to parse voice response: {e}")


if __name__ == '__main__':
  dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

  text = "How's the weather today?"
  # SpeechSynthesizer interface usage: dashscope.audio.qwen_tts.SpeechSynthesizer.call(...)
  response = dashscope.MultiModalConversation.call(
    model=DEFAULT_TARGET_MODEL,
    # If you haven't configured an environment variable, replace the following line with: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    text=text,
    voice=create_voice(VOICE_FILE_PATH), # Replace the voice parameter with the custom voice generated by cloning
    stream=False
  )
  print(response)