mirror of
https://github.com/langgenius/dify.git
synced 2026-04-27 05:58:14 +08:00
Fix voice selection (#2664)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
This commit is contained in:
@ -88,7 +88,7 @@ class ChatMessageTextApi(Resource):
|
||||
response = AudioService.transcript_tts(
|
||||
tenant_id=app_model.tenant_id,
|
||||
text=request.form['text'],
|
||||
voice=app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
voice=request.form['voice'] if request.form['voice'] else app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
streaming=False
|
||||
)
|
||||
|
||||
|
||||
@ -85,7 +85,7 @@ class ChatTextApi(InstalledAppResource):
|
||||
response = AudioService.transcript_tts(
|
||||
tenant_id=app_model.tenant_id,
|
||||
text=request.form['text'],
|
||||
voice=app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
voice=request.form['voice'] if request.form['voice'] else app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
streaming=False
|
||||
)
|
||||
return {'data': response.data.decode('latin1')}
|
||||
|
||||
@ -87,7 +87,7 @@ class TextApi(Resource):
|
||||
tenant_id=app_model.tenant_id,
|
||||
text=args['text'],
|
||||
end_user=end_user,
|
||||
voice=app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
voice=args['voice'] if args['voice'] else app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
streaming=args['streaming']
|
||||
)
|
||||
|
||||
|
||||
@ -84,7 +84,7 @@ class TextApi(WebApiResource):
|
||||
tenant_id=app_model.tenant_id,
|
||||
text=request.form['text'],
|
||||
end_user=end_user.external_user_id,
|
||||
voice=app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
voice=request.form['voice'] if request.form['voice'] else app_model.app_model_config.text_to_speech_dict.get('voice'),
|
||||
streaming=False
|
||||
)
|
||||
|
||||
|
||||
@ -34,7 +34,7 @@ class OpenAIText2SpeechModel(_CommonOpenAI, TTSModel):
|
||||
:return: text translated to audio file
|
||||
"""
|
||||
audio_type = self._get_model_audio_type(model, credentials)
|
||||
if not voice:
|
||||
if not voice or voice not in [d['value'] for d in self.get_tts_model_voices(model=model, credentials=credentials)]:
|
||||
voice = self._get_model_default_voice(model, credentials)
|
||||
if streaming:
|
||||
return Response(stream_with_context(self._tts_invoke_streaming(model=model,
|
||||
|
||||
@ -34,7 +34,7 @@ class TongyiText2SpeechModel(_CommonTongyi, TTSModel):
|
||||
:return: text translated to audio file
|
||||
"""
|
||||
audio_type = self._get_model_audio_type(model, credentials)
|
||||
if not voice or voice not in self.get_tts_model_voices(model=model, credentials=credentials):
|
||||
if not voice or voice not in [d['value'] for d in self.get_tts_model_voices(model=model, credentials=credentials)]:
|
||||
voice = self._get_model_default_voice(model, credentials)
|
||||
if streaming:
|
||||
return Response(stream_with_context(self._tts_invoke_streaming(model=model,
|
||||
|
||||
Reference in New Issue
Block a user