- replaced old TranscriptionModels/LLMModels/SupportsX methods with Models() []Model
- added DefaultModel(t ModelType), IsLocal() to interface
- added helpers: GetModel, ModelsOfType, FindModelByID, ModelsForLanguage, ValidateModelLanguage
- all providers now return full Model metadata with SupportedLanguages, AdapterType, Endpoint
- groq distil-whisper-large-v3-en marked as english-only
- updated TUI to use new interface
- add Providers map for centralized API key storage
- add Keywords global field for transcription/LLM hints
- add LLMConfig with Enabled, Provider, Model
- add LLMPostProcessingConfig (RemoveStutters, AddPunctuation, FixGrammar, RemoveFillerWords)
- add LLMCustomPromptConfig (Enabled, Prompt)
- add ToLLMConfig() and IsLLMEnabled() methods
- add auto-migration from old transcription.api_key format
- unified API key resolution: providers -> legacy -> env var
- backward compatible with existing configs
Allow users to customize notification messages via config.toml.
Messages fall back to defaults when not configured, preserving
existing behavior. Supports custom text or emoji-only notifications.
Configuration example:
[notifications.messages.recording_started]
title = ""
body = "🎤"
Add support for Groq Whisper API as an alternative to OpenAI:
- groq-transcription: Fast transcription using whisper-large-v3 or whisper-large-v3-turbo
- groq-translation: Translation to English (whisper-large-v3 only)
Features:
- New transcription adapters for both Groq services
- Config validation with provider-specific model restrictions
- API key support via config file or GROQ_API_KEY environment variable
- Updated interactive configuration wizard with provider selection
- Comprehensive test coverage for all providers
- Shared WAV conversion utility for audio preprocessing
Breaking changes: None
Backward compatibility: Existing OpenAI configurations continue to work unchanged
leonardotrapani