diff --git a/backend/open_webui/routers/audio.py b/backend/open_webui/routers/audio.py index a970366d1..12c9dbc6d 100644 --- a/backend/open_webui/routers/audio.py +++ b/backend/open_webui/routers/audio.py @@ -680,7 +680,18 @@ def transcription( def get_available_models(request: Request) -> list[dict]: available_models = [] if request.app.state.config.TTS_ENGINE == "openai": - available_models = [{"id": "tts-1"}, {"id": "tts-1-hd"}] + # Use custom endpoint if not using the official OpenAI API URL + if not request.app.state.config.TTS_OPENAI_API_BASE_URL.startswith("https://api.openai.com"): + try: + response = requests.get(f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/models") + response.raise_for_status() + data = response.json() + available_models = data.get("models", []) + except Exception as e: + log.error(f"Error fetching models from custom endpoint: {str(e)}") + available_models = [] + else: + available_models = [{"id": "tts-1"}, {"id": "tts-1-hd"}] elif request.app.state.config.TTS_ENGINE == "elevenlabs": try: response = requests.get( @@ -711,14 +722,26 @@ def get_available_voices(request) -> dict: """Returns {voice_id: voice_name} dict""" available_voices = {} if request.app.state.config.TTS_ENGINE == "openai": - available_voices = { - "alloy": "alloy", - "echo": "echo", - "fable": "fable", - "onyx": "onyx", - "nova": "nova", - "shimmer": "shimmer", - } + # Use custom endpoint if not using the official OpenAI API URL + if not request.app.state.config.TTS_OPENAI_API_BASE_URL.startswith("https://api.openai.com"): + try: + response = requests.get(f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/voices") + response.raise_for_status() + data = response.json() + voices_list = data.get("voices", []) + available_voices = {voice["id"]: voice["name"] for voice in voices_list} + except Exception as e: + log.error(f"Error fetching voices from custom endpoint: {str(e)}") + available_voices = {} + else: + available_voices = { + "alloy": "alloy", + "echo": "echo", + "fable": "fable", + "onyx": "onyx", + "nova": "nova", + "shimmer": "shimmer", + } elif request.app.state.config.TTS_ENGINE == "elevenlabs": try: available_voices = get_elevenlabs_voices(