CosyVoice Python SDK

# coding=utf-8

import os
import json
import dashscope
from dashscope.audio.tts_v2 import *

from datetime import datetime

def get_timestamp():
    now = datetime.now()
    formatted_timestamp = now.strftime("[%Y-%m-%d %H:%M:%S.%f]")
    return formatted_timestamp

# The API Keys for Singapore and Beijing regions are different. Get API Key: https://help.aliyun.com/model-studio/get-api-key
# If environment variable is not configured, replace the following line with your Model Studio API Key: dashscope.api_key = "sk-xxx"
dashscope.api_key = os.environ.get('DASHSCOPE_API_KEY')

# The following configuration is for the China (Beijing) region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
dashscope.base_websocket_api_url='wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference'

# Model
model = "cosyvoice-v3-plus"
# Voice
voice = "longanyang"

# Define callback interface
class Callback(ResultCallback):
    _player = None
    _stream = None

    def on_open(self):
        self.file = open("output.mp3", "wb")
        print("Connection established: " + get_timestamp())

    def on_complete(self):
        print("Speech synthesis completed, all results received: " + get_timestamp())
        # After the task completes (on_complete callback triggered), you can call get_first_package_delay to get the latency
        # The first text submission requires establishing a WebSocket connection, so the first packet latency includes the connection setup time
        print('[Metric] requestId: {}, first packet latency: {} ms'.format(
            synthesizer.get_last_request_id(),
            synthesizer.get_first_package_delay()))

    def on_error(self, message: str):
        print(f"Speech synthesis error: {message}")

    def on_close(self):
        print("Connection closed: " + get_timestamp())
        self.file.close()

    def on_event(self, message):
        # Parse server-side events and get output information
        data = json.loads(message)
        output = data.get('payload', {}).get('output', {})
        event_type = output.get('type', '')
        original_text = output.get('original_text', '')
        if event_type:
            print(f"Event type: {event_type}, original text: {original_text}")

    def on_data(self, data: bytes) -> None:
        print(get_timestamp() + " Binary audio length: " + str(len(data)))
        self.file.write(data)

callback = Callback()

# Instantiate SpeechSynthesizer, passing request parameters such as model and voice in the constructor
synthesizer = SpeechSynthesizer(
    model=model,
    voice=voice,
    callback=callback,
)

# Send text for synthesis and get binary audio in real time via the on_data callback method
synthesizer.call("How is the weather today?")

# coding=utf-8
#
# pyaudio installation instructions:
# For macOS, run the following commands:
#   brew install portaudio
#   pip install pyaudio
# For Debian/Ubuntu, run the following commands:
#   sudo apt-get install python-pyaudio python3-pyaudio
#   or
#   pip install pyaudio
# For CentOS, run the following commands:
#   sudo yum install -y portaudio portaudio-devel && pip install pyaudio
# For Microsoft Windows, run the following command:
#   python -m pip install pyaudio

import os
import time
import pyaudio
import json
import dashscope
from dashscope.api_entities.dashscope_response import SpeechSynthesisResponse
from dashscope.audio.tts_v2 import *

from datetime import datetime

def get_timestamp():
    now = datetime.now()
    formatted_timestamp = now.strftime("[%Y-%m-%d %H:%M:%S.%f]")
    return formatted_timestamp

# The API Keys for Singapore and Beijing regions are different. Get API Key: https://help.aliyun.com/model-studio/get-api-key
# If environment variable is not configured, replace the following line with your Model Studio API Key: dashscope.api_key = "sk-xxx"
dashscope.api_key = os.environ.get('DASHSCOPE_API_KEY')

# The following configuration is for the China (Beijing) region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
dashscope.base_websocket_api_url='wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference'

# Model
model = "cosyvoice-v3-plus"
# Voice
voice = "longanyang"

# Define callback interface
class Callback(ResultCallback):
    _player = None
    _stream = None

    def on_open(self):
        print("Connection established: " + get_timestamp())
        self._player = pyaudio.PyAudio()
        self._stream = self._player.open(
            format=pyaudio.paInt16, channels=1, rate=22050, output=True
        )

    def on_complete(self):
        print("Speech synthesis completed, all results received: " + get_timestamp())

    def on_error(self, message: str):
        print(f"Speech synthesis error: {message}")

    def on_close(self):
        print("Connection closed: " + get_timestamp())
        # Stop the player
        self._stream.stop_stream()
        self._stream.close()
        self._player.terminate()

    def on_event(self, message):
        # Parse server-side events and get output information
        data = json.loads(message)
        output = data.get('payload', {}).get('output', {})
        event_type = output.get('type', '')
        original_text = output.get('original_text', '')
        if event_type:
            print(f"Event type: {event_type}, original text: {original_text}")

    def on_data(self, data: bytes) -> None:
        print(get_timestamp() + " Binary audio length: " + str(len(data)))
        self._stream.write(data)

callback = Callback()

test_text = [
    "Streaming text-to-speech SDK,",
    "converts input text",
    "into binary audio data.",
    "Compared with non-streaming speech synthesis,",
    "streaming synthesis offers better real-time performance.",
    "Users hear near-synchronous audio output while typing,",
    "greatly improving interaction experience",
    "and reducing wait time.",
    "Ideal for large language model (LLM) integration,",
    "where text is streamed for speech synthesis.",
]

# Instantiate SpeechSynthesizer, passing request parameters such as model and voice in the constructor
synthesizer = SpeechSynthesizer(
    model=model,
    voice=voice,
    format=AudioFormat.PCM_22050HZ_MONO_16BIT,
    callback=callback,
)

# Send text for streaming synthesis. Get binary audio in real time via the on_data callback method
for text in test_text:
    synthesizer.streaming_call(text)
    time.sleep(0.1)
# End streaming speech synthesis
synthesizer.streaming_complete()

# The first text submission requires establishing a WebSocket connection, so the first packet latency includes the connection setup time
print('[Metric] requestId: {}, first packet latency: {} ms'.format(
    synthesizer.get_last_request_id(),
    synthesizer.get_first_package_delay()))