Skip to main content
AI commands enable post-processing of transcriptions using large language models for grammar correction, formatting, and punctuation.

AI Settings

get_ai_settings

Get current AI enhancement settings.
Returns:
Usage:

get_ai_settings_for_provider

Get AI settings for a specific provider.
string
required
Provider name: "openai", "gemini", or "custom"
Usage:

update_ai_settings

Update AI enhancement settings.
boolean
required
Enable or disable AI enhancement
string
required
AI provider: "openai", "gemini", or "custom"
string
required
Model ID (e.g., "gpt-5-nano", "gemini-3-flash-preview")
Usage:
Errors:
  • "Please select a model before enabling AI enhancement" - Model empty
  • "API key not found. Please add an API key first." - No API key cached

disable_ai_enhancement

Disable AI enhancement.
Usage:

API Key Management

cache_ai_api_key

Cache an API key for backend use (called on app startup).
string
required
Provider: "openai", "gemini", or "custom"
string
required
API key to cache
Usage:
Note: This command does NOT validate the API key. Use validate_and_cache_api_key for new keys.

validate_and_cache_api_key

Validate and cache a new API key.
string
required
Provider: "openai", "gemini", or "custom"
string
API key (optional for noAuth: true)
string
Custom base URL (for OpenAI-compatible APIs)
string
Model to test (defaults to "gpt-5-nano")
boolean
Skip authentication (for local LLMs)
Usage:
Validation:
  1. For OpenAI/custom: Sends test request to /v1/models or /v1/chat/completions
  2. Checks if specified model exists
  3. Caches key only if validation succeeds
Errors:
  • "HTTP 401: Unauthorized" - Invalid API key
  • "Model 'xyz' not found in endpoint model list" - Model doesn’t exist
  • "Network error" - Connection failed

test_openai_endpoint

Test an OpenAI-compatible endpoint without saving.
string
required
Base URL (e.g., "http://localhost:1234/v1")
string
required
Model to test
string
API key (optional)
boolean
Skip authentication
Usage:

clear_ai_api_key_cache

Clear cached API key for a provider.
string
required
Provider to clear
Usage:

Enhancement

enhance_transcription

Enhance transcribed text using AI.
string
required
Raw transcription text to enhance
Returns: Enhanced text with proper grammar, punctuation, and formatting Usage:
Behavior:
  1. Checks if AI is enabled in settings
  2. Returns original text if disabled
  3. Loads provider config (API key, base URL, model)
  4. Sends text to LLM with enhancement prompt
  5. Returns formatted response
Enhancement Options: See get_enhancement_options and update_enhancement_options for customization. Errors:
  • "AI enhancement is disabled" - Not enabled in settings
  • "API key not found in cache" - Missing API key
  • "AI formatting failed: ..." - LLM request failed

get_enhancement_options

Get AI enhancement formatting options.
Returns:
Usage:

update_enhancement_options

Update AI enhancement options.
string
required
Formatting preset: "professional", "casual", "technical", or "creative"
string
Additional instructions for the LLM
Usage:

Provider Models

list_provider_models

Get curated list of models for a provider.
string
required
Provider: "openai" or "gemini"
Returns:
Usage:
Available Models: OpenAI:
  • gpt-5-nano - GPT-5 Nano (recommended)
  • gpt-5-mini - GPT-5 Mini (recommended)
Gemini:
  • gemini-3-flash-preview - Gemini 3 Flash (recommended)
  • gemini-2.5-flash - Gemini 2.5 Flash (recommended)
  • gemini-2.5-flash-lite - Gemini 2.5 Flash Lite (recommended)

OpenAI Configuration

set_openai_config

Configure OpenAI-compatible endpoint.
string
required
Base URL (e.g., "http://localhost:1234/v1")
boolean
Skip authentication (optional)
Usage:

get_openai_config

Get current OpenAI configuration.
Returns:
Usage:

Supported Providers

See Also