estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Display selected tts voice name (#2459)

Browse Source 
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:
Charlie.Wei
2024-02-18 15:39:25 +08:00
committed by GitHub
parent 963d9b6032
commit c6e2900be7
10 changed files with 28 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
api/core/model_runtime/model_providers/__base/tts_model.py
View File

@@ -53,7 +53,7 @@ class TTSModel(AIModel):
"""
raise NotImplementedError
def get_tts_model_voices(self, model: str, credentials: dict, language: str) -> list:
def get_tts_model_voices(self, model: str, credentials: dict, language: Optional[str] = None) -> list:
"""
Get voice for given tts model voices
@@ -66,7 +66,10 @@ class TTSModel(AIModel):
if model_schema and ModelPropertyKey.VOICES in model_schema.model_properties:
voices = model_schema.model_properties[ModelPropertyKey.VOICES]
return [{'name': d['name'], 'value': d['mode']} for d in voices if language and language in d.get('language')]
if language:
return [{'name': d['name'], 'value': d['mode']} for d in voices if language and language in d.get('language')]
else:
return [{'name': d['name'], 'value': d['mode']} for d in voices]
def _get_model_default_voice(self, model: str, credentials: dict) -> any:
"""

2
api/core/model_runtime/model_providers/openai/tts/tts.py
View File

@@ -119,7 +119,7 @@ class OpenAIText2SpeechModel(_CommonOpenAI, TTSModel):
"""
# transform credentials to kwargs for model instance
credentials_kwargs = self._to_credential_kwargs(credentials)
if not voice:
if not voice or voice not in self.get_tts_model_voices(model=model, credentials=credentials):
voice = self._get_model_default_voice(model, credentials)
word_limit = self._get_model_word_limit(model, credentials)
audio_type = self._get_model_audio_type(model, credentials)

2
api/core/model_runtime/model_providers/tongyi/tts/tts.py
View File

@@ -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:
if not voice or voice not 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,