OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-06-15 02:41:30 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

remove dependency and migrate to raw rest calls

Browse Source
This commit is contained in:
Pawel Ochman 2024-09-18 12:24:55 +01:00
parent d6b68f405e
commit eacb69074e
2 changed files with 20 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
backend/open_webui/apps/audio/main.py
View File

@ -309,20 +309,33 @@ async def speech(request: Request, user=Depends(get_verified_user)):
log.exception(e) log.exception(e)
raise HTTPException(status_code=400, detail="Invalid JSON payload") raise HTTPException(status_code=400, detail="Invalid JSON payload")
import azure.cognitiveservices.speech as speechsdk region = "uksouth"
language = "en-GB-SoniaNeural"
locale = "en-GB"
output_format = "audio-24khz-160kbitrate-mono-mp3"
url = f"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1"
config = speechsdk.SpeechConfig(subscription=app.state.config.TTS_API_KEY, region="uksouth") headers = {
speaker_config = speechsdk.audio.AudioOutputConfig(use_default_speaker=False, filename=str(file_path)) 'Ocp-Apim-Subscription-Key': app.state.config.TTS_API_KEY,
'Content-Type': 'application/ssml+xml',
'X-Microsoft-OutputFormat': output_format
}
client = speechsdk.SpeechSynthesizer(speech_config=config, audio_config=speaker_config) data = f"""<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="{locale}">
result = client.speak_text(payload["input"]) <voice name="{language}">{payload["input"]}</voice>
</speak>"""
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted: response = requests.post(url, headers=headers, data=data)
if response.status_code == 200:
with open(file_path, "wb") as f:
f.write(response.content)
return FileResponse(file_path) return FileResponse(file_path)
else: else:
log.error(f"Error synthesizing speech - {response.reason}")
raise HTTPException( raise HTTPException(
status_code=500, status_code=500,
detail=f"Error synthesizing speech - {result.reason}") detail=f"Error synthesizing speech - {response.reason}")

2
backend/requirements.txt
View File

@ -79,8 +79,6 @@ extract_msg
pydub pydub
duckduckgo-search~=6.2.11 duckduckgo-search~=6.2.11
azure-cognitiveservices-speech==1.40.0
## Tests ## Tests
docker~=7.1.0 docker~=7.1.0
pytest~=8.3.2 pytest~=8.3.2