Skip to main content

Environment Variables

Environment Variables List​

info

For a complete list of all Open WebUI environment variables, see the Environment Variable Configuration page.

The following is a summary of the environment variables for speech to text (STT) and text to speech (TTS).

UI Configuration

Most of these settings can also be configured in the Admin Panel → Settings → Audio tab. Environment variables take precedence on startup but can be overridden in the UI.

Speech To Text (STT) Environment Variables​

Local Whisper​

VariableDescriptionDefault
WHISPER_MODELWhisper model sizebase
WHISPER_MODEL_DIRDirectory to store Whisper model files{CACHE_DIR}/whisper/models
WHISPER_COMPUTE_TYPECompute type for inference (see note below)int8
WHISPER_LANGUAGEISO 639-1 language code (empty = auto-detect)empty
WHISPER_MULTILINGUALUse the multilingual Whisper modelfalse
WHISPER_MODEL_AUTO_UPDATEAuto-download model updatesfalse
WHISPER_VAD_FILTEREnable Voice Activity Detection filterfalse
WHISPER_COMPUTE_TYPE Options
  • int8 — CPU default, fastest but may not work on older GPUs
  • float16 — Recommended for CUDA/GPU
  • int8_float16 — Hybrid mode (int8 weights, float16 computation)
  • float32 — Maximum compatibility, slowest

If using the :cuda Docker image with an older GPU, set WHISPER_COMPUTE_TYPE=float16 to avoid errors.

OpenAI-Compatible STT​

VariableDescriptionDefault
AUDIO_STT_ENGINESTT engine: empty (local Whisper), openai, azure, deepgram, mistralempty
AUDIO_STT_MODELSTT model for external providersempty
AUDIO_STT_OPENAI_API_BASE_URLOpenAI-compatible API base URLhttps://api.openai.com/v1
AUDIO_STT_OPENAI_API_KEYOpenAI API keyempty
AUDIO_STT_SUPPORTED_CONTENT_TYPESComma-separated list of supported audio MIME typesempty

Azure STT​

VariableDescriptionDefault
AUDIO_STT_AZURE_API_KEYAzure Cognitive Services API keyempty
AUDIO_STT_AZURE_REGIONAzure regioneastus
AUDIO_STT_AZURE_LOCALESComma-separated locales (e.g., en-US,de-DE)auto
AUDIO_STT_AZURE_BASE_URLCustom Azure base URL (optional)empty
AUDIO_STT_AZURE_MAX_SPEAKERSMax speakers for diarization3

Deepgram STT​

VariableDescriptionDefault
DEEPGRAM_API_KEYDeepgram API keyempty

Mistral STT​

VariableDescriptionDefault
AUDIO_STT_MISTRAL_API_KEYMistral API keyempty
AUDIO_STT_MISTRAL_API_BASE_URLMistral API base URLhttps://api.mistral.ai/v1
AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONSUse chat completions endpointfalse

Text To Speech (TTS) Environment Variables​

General TTS​

VariableDescriptionDefault
AUDIO_TTS_ENGINETTS engine: empty (disabled), openai, elevenlabs, azure, transformersempty
AUDIO_TTS_MODELTTS modeltts-1
AUDIO_TTS_VOICEDefault voicealloy
AUDIO_TTS_SPLIT_ONSplit text on: punctuation or nonepunctuation
AUDIO_TTS_API_KEYAPI key for ElevenLabs or Azure TTSempty

OpenAI-Compatible TTS​

VariableDescriptionDefault
AUDIO_TTS_OPENAI_API_BASE_URLOpenAI-compatible TTS API base URLhttps://api.openai.com/v1
AUDIO_TTS_OPENAI_API_KEYOpenAI TTS API keyempty
AUDIO_TTS_OPENAI_PARAMSAdditional JSON params for OpenAI TTSempty

Azure TTS​

VariableDescriptionDefault
AUDIO_TTS_AZURE_SPEECH_REGIONAzure Speech regioneastus
AUDIO_TTS_AZURE_SPEECH_BASE_URLCustom Azure Speech base URL (optional)empty
AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMATAudio output formataudio-24khz-160kbitrate-mono-mp3

Tips for Configuring Audio​

Using Local Whisper STT​

For GPU acceleration issues or older GPUs, try setting:

environment:
  - WHISPER_COMPUTE_TYPE=float16

Using External TTS Services​

When running Open WebUI in Docker with an external TTS service:

environment:
  - AUDIO_TTS_ENGINE=openai
  - AUDIO_TTS_OPENAI_API_BASE_URL=http://host.docker.internal:5050/v1
  - AUDIO_TTS_OPENAI_API_KEY=your-api-key
tip

Use host.docker.internal on Docker Desktop (Windows/Mac) to access services on the host. On Linux, use the host IP or container networking.

For troubleshooting audio issues, see the Audio Troubleshooting Guide.