Emil_Shanaty/open-webui-ai4me
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refac/enh: openai tts additional params support

Browse Source
This commit is contained in:
Timothy Jaeryang Baek
2025-10-02 03:52:29 -05:00
parent a1fc99c66f
commit 5d5b42d3f5
4 changed files with 65 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/config.py
+13
View File
@@ -3361,6 +3361,19 @@ AUDIO_TTS_OPENAI_API_KEY = PersistentConfig(
os.getenv("AUDIO_TTS_OPENAI_API_KEY", OPENAI_API_KEY),
)
audio_tts_openai_params = os.getenv("AUDIO_TTS_OPENAI_PARAMS", "")
try:
audio_tts_openai_params = json.loads(audio_tts_openai_params)
except json.JSONDecodeError:
audio_tts_openai_params = {}
AUDIO_TTS_OPENAI_PARAMS = PersistentConfig(
"AUDIO_TTS_OPENAI_PARAMS",
"audio.tts.openai.params",
audio_tts_openai_params,
)
AUDIO_TTS_API_KEY = PersistentConfig(
"AUDIO_TTS_API_KEY",
"audio.tts.api_key",
backend/open_webui/main.py
+9 -4
View File
@@ -175,13 +175,14 @@ from open_webui.config import (
AUDIO_STT_AZURE_LOCALES,
AUDIO_STT_AZURE_BASE_URL,
AUDIO_STT_AZURE_MAX_SPEAKERS,
AUDIO_TTS_API_KEY,
AUDIO_TTS_ENGINE,
AUDIO_TTS_MODEL,
AUDIO_TTS_VOICE,
AUDIO_TTS_OPENAI_API_BASE_URL,
AUDIO_TTS_OPENAI_API_KEY,
AUDIO_TTS_OPENAI_PARAMS,
AUDIO_TTS_API_KEY,
AUDIO_TTS_SPLIT_ON,
AUDIO_TTS_VOICE,
AUDIO_TTS_AZURE_SPEECH_REGION,
AUDIO_TTS_AZURE_SPEECH_BASE_URL,
AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT,
@@ -1096,11 +1097,15 @@ app.state.config.AUDIO_STT_AZURE_LOCALES = AUDIO_STT_AZURE_LOCALES
app.state.config.AUDIO_STT_AZURE_BASE_URL = AUDIO_STT_AZURE_BASE_URL
app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS = AUDIO_STT_AZURE_MAX_SPEAKERS
app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE
app.state.config.TTS_MODEL = AUDIO_TTS_MODEL
app.state.config.TTS_VOICE = AUDIO_TTS_VOICE
app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
app.state.config.TTS_OPENAI_PARAMS = AUDIO_TTS_OPENAI_PARAMS
app.state.config.TTS_API_KEY = AUDIO_TTS_API_KEY
app.state.config.TTS_SPLIT_ON = AUDIO_TTS_SPLIT_ON
backend/open_webui/routers/audio.py
+12 -3
View File
@@ -154,6 +154,7 @@ def set_faster_whisper_model(model: str, auto_update: bool = False):
class TTSConfigForm(BaseModel):
OPENAI_API_BASE_URL: str
OPENAI_API_KEY: str
OPENAI_PARAMS: Optional[dict] = None
API_KEY: str
ENGINE: str
MODEL: str
@@ -190,6 +191,7 @@ async def get_audio_config(request: Request, user=Depends(get_admin_user)):
"tts": {
"OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
"OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
"OPENAI_PARAMS": request.app.state.config.TTS_OPENAI_PARAMS,
"API_KEY": request.app.state.config.TTS_API_KEY,
"ENGINE": request.app.state.config.TTS_ENGINE,
"MODEL": request.app.state.config.TTS_MODEL,
@@ -222,6 +224,7 @@ async def update_audio_config(
):
request.app.state.config.TTS_OPENAI_API_BASE_URL = form_data.tts.OPENAI_API_BASE_URL
request.app.state.config.TTS_OPENAI_API_KEY = form_data.tts.OPENAI_API_KEY
request.app.state.config.TTS_OPENAI_PARAMS = form_data.tts.OPENAI_PARAMS
request.app.state.config.TTS_API_KEY = form_data.tts.API_KEY
request.app.state.config.TTS_ENGINE = form_data.tts.ENGINE
request.app.state.config.TTS_MODEL = form_data.tts.MODEL
@@ -262,12 +265,13 @@ async def update_audio_config(
return {
"tts": {
"OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
"OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
"API_KEY": request.app.state.config.TTS_API_KEY,
"ENGINE": request.app.state.config.TTS_ENGINE,
"MODEL": request.app.state.config.TTS_MODEL,
"VOICE": request.app.state.config.TTS_VOICE,
"OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
"OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
"OPENAI_PARAMS": request.app.state.config.TTS_OPENAI_PARAMS,
"API_KEY": request.app.state.config.TTS_API_KEY,
"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,
@@ -337,6 +341,11 @@ async def speech(request: Request, user=Depends(get_verified_user)):
async with aiohttp.ClientSession(
timeout=timeout, trust_env=True
) as session:
payload = {
**payload,
**(request.app.state.config.TTS_OPENAI_PARAMS or {}),
}
r = await session.post(
url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
json=payload,