OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-06-26 18:26:48 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #13540 from NoMoreFood/dev

Browse Source 
feat: Azure TTS Allow Base URL
This commit is contained in:
Tim Jaeryang Baek
2025-05-07 00:49:57 +04:00
committed by GitHub
parent e0e151f4f4 5c055b73a3
commit 2a4dfc02a2
4 changed files with 76 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
backend/open_webui/routers/audio.py
View File

@@ -138,6 +138,7 @@ class TTSConfigForm(BaseModel):
VOICE: str
SPLIT_ON: str
AZURE_SPEECH_REGION: str
AZURE_SPEECH_BASE_URL: str
AZURE_SPEECH_OUTPUT_FORMAT: str
@@ -172,6 +173,7 @@ async def get_audio_config(request: Request, user=Depends(get_admin_user)):
"VOICE": request.app.state.config.TTS_VOICE,
"SPLIT_ON": request.app.state.config.TTS_SPLIT_ON,
"AZURE_SPEECH_REGION": request.app.state.config.TTS_AZURE_SPEECH_REGION,
"AZURE_SPEECH_BASE_URL": request.app.state.config.TTS_AZURE_SPEECH_BASE_URL,
"AZURE_SPEECH_OUTPUT_FORMAT": request.app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT,
},
"stt": {
@@ -202,6 +204,9 @@ async def update_audio_config(
request.app.state.config.TTS_VOICE = form_data.tts.VOICE
request.app.state.config.TTS_SPLIT_ON = form_data.tts.SPLIT_ON
request.app.state.config.TTS_AZURE_SPEECH_REGION = form_data.tts.AZURE_SPEECH_REGION
request.app.state.config.TTS_AZURE_SPEECH_BASE_URL = (
form_data.tts.AZURE_SPEECH_BASE_URL
)
request.app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT = (
form_data.tts.AZURE_SPEECH_OUTPUT_FORMAT
)
@@ -235,6 +240,7 @@ async def update_audio_config(
"VOICE": request.app.state.config.TTS_VOICE,
"SPLIT_ON": request.app.state.config.TTS_SPLIT_ON,
"AZURE_SPEECH_REGION": request.app.state.config.TTS_AZURE_SPEECH_REGION,
"AZURE_SPEECH_BASE_URL": request.app.state.config.TTS_AZURE_SPEECH_BASE_URL,
"AZURE_SPEECH_OUTPUT_FORMAT": request.app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT,
},
"stt": {
@@ -406,7 +412,8 @@ async def speech(request: Request, user=Depends(get_verified_user)):
log.exception(e)
raise HTTPException(status_code=400, detail="Invalid JSON payload")
region = request.app.state.config.TTS_AZURE_SPEECH_REGION
region = request.app.state.config.TTS_AZURE_SPEECH_REGION or "eastus"
base_url = request.app.state.config.TTS_AZURE_SPEECH_BASE_URL
language = request.app.state.config.TTS_VOICE
locale = "-".join(request.app.state.config.TTS_VOICE.split("-")[:1])
output_format = request.app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT
@@ -420,7 +427,8 @@ async def speech(request: Request, user=Depends(get_verified_user)):
timeout=timeout, trust_env=True
) as session:
async with session.post(
f"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1",
(base_url or f"https://{region}.tts.speech.microsoft.com")
+ "/cognitiveservices/v1",
headers={
"Ocp-Apim-Subscription-Key": request.app.state.config.TTS_API_KEY,
"Content-Type": "application/ssml+xml",
@@ -651,10 +659,10 @@ def transcribe(request: Request, file_path):
)
api_key = request.app.state.config.AUDIO_STT_AZURE_API_KEY
region = request.app.state.config.AUDIO_STT_AZURE_REGION
region = request.app.state.config.AUDIO_STT_AZURE_REGION or "eastus"
locales = request.app.state.config.AUDIO_STT_AZURE_LOCALES
base_url = request.app.state.config.AUDIO_STT_AZURE_BASE_URL
max_speakers = request.app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS
max_speakers = request.app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS or 3
# IF NO LOCALES, USE DEFAULTS
if len(locales) < 2:
@@ -681,12 +689,6 @@ def transcribe(request: Request, file_path):
detail="Azure API key is required for Azure STT",
)
if not base_url and not region:
raise HTTPException(
status_code=400,
detail="Azure region or base url is required for Azure STT",
)
r = None
try:
# Prepare the request
@@ -702,9 +704,8 @@ def transcribe(request: Request, file_path):
}
url = (
base_url
or f"https://{region}.api.cognitive.microsoft.com/speechtotext/transcriptions:transcribe?api-version=2024-11-15"
)
base_url or f"https://{region}.api.cognitive.microsoft.com"
) + "/speechtotext/transcriptions:transcribe?api-version=2024-11-15"
# Use context manager to ensure file is properly closed
with open(file_path, "rb") as audio_file:
@@ -939,7 +940,10 @@ def get_available_voices(request) -> dict:
elif request.app.state.config.TTS_ENGINE == "azure":
try:
region = request.app.state.config.TTS_AZURE_SPEECH_REGION
url = f"https://{region}.tts.speech.microsoft.com/cognitiveservices/voices/list"
base_url = request.app.state.config.TTS_AZURE_SPEECH_BASE_URL
url = (
base_url or f"https://{region}.tts.speech.microsoft.com"
) + "/cognitiveservices/voices/list"
headers = {
"Ocp-Apim-Subscription-Key": request.app.state.config.TTS_API_KEY
}