语音合成 Sambert Python SDK

# coding=utf-8
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,
                                format='wav')
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()))

# coding=utf-8
import sys
from dashscope.api_entities.dashscope_response import SpeechSynthesisResponse
from dashscope.audio.tts import ResultCallback, SpeechSynthesizer, SpeechSynthesisResult

class Callback(ResultCallback):
  def on_open(self):
    print('Speech synthesizer is opened.')

  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.')

  def on_event(self, result: SpeechSynthesisResult):
    if result.get_audio_frame() is not None:
      print('audio result length:', sys.getsizeof(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='今天天气怎么样',
                       sample_rate=48000,
                       callback=callback,
                       word_timestamp_enabled=True,
                       phoneme_timestamp_enabled=True)

class Callback(ResultCallback):
  def on_open(self):
    print('和服务器成功建立连接')

  def on_complete(self):
    print('任务完成')

  def on_error(self, response: SpeechSynthesisResponse):
    print('报错：%s' % (str(response)))

  def on_close(self):
    print('和服务器之间的连接已关闭')

  def on_event(self, result: SpeechSynthesisResult):
    if result.get_audio_frame() is not None:
      print('收到二进制音频数据：', result.get_audio_frame())
    if result.get_timestamp() is not None:
      print('收到时间戳数据：', str(result.get_timestamp()))

callback = Callback()

{
  "begin_time": 0,
  "end_time": 1412,
  "words": [
    {
      "text": "今",
      "begin_time": 0,
      "end_time": 200,
      "phonemes": [
        {"begin_time": 0, "end_time": 82, "text": "j_c", "tone": 1},
        {"begin_time": 82, "end_time": 200, "text": "in_c", "tone": 1}
      ]
    }
  ]
}