Skip to content

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

feat: add Claude 4.6, Gemini 3 Flash, and Gemini 3.1 Pro models (#301)

Adam Holter9ae751a49879
diff --git a/CLAUDE.md b/CLAUDE.md
index a45d1c44c..7f85bddc2 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -110,7 +110,7 @@ OpenWhispr is an Electron-based desktop dictation application that uses whisper.
- Detects when user addresses their named agent
- Routes to appropriate AI provider (OpenAI/Anthropic/Gemini)
- Removes agent name from final output
- - Supports GPT-5, Claude Opus 4.1, and Gemini 2.5 models
+ - Supports GPT-5, Claude 4.6 (Opus/Sonnet/Haiku), and Gemini 3.1 Pro / 3 Flash models
### whisper.cpp Integration
@@ -237,14 +237,13 @@ Environment variables persisted to `.env` (via `saveAllKeysToEnvFile()`):
- GPT-5 Nano (`gpt-5-nano`) - Ultra-fast, low latency
- GPT-4.1 Series (`gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`) - Strong baseline with 1M context
- **Anthropic** (Via IPC bridge to avoid CORS):
- - Claude Sonnet 4.5 (`claude-sonnet-4-5`) - Balanced performance
+ - Claude Sonnet 4.6 (`claude-sonnet-4-6`) - Balanced performance
- Claude Haiku 4.5 (`claude-haiku-4-5`) - Fast with near-frontier intelligence
- - Claude Opus 4.5 (`claude-opus-4-5`) - Most capable Claude model
+ - Claude Opus 4.6 (`claude-opus-4-6`) - Most capable Claude model
- **Google Gemini** (Direct API integration):
- - Gemini 2.5 Pro (`gemini-2.5-pro`) - Most capable Gemini model
- - Gemini 2.5 Flash (`gemini-2.5-flash`) - High-performance with thinking
+ - Gemini 3.1 Pro (`gemini-3.1-pro-preview`) - Most capable Gemini model
+ - Gemini 3 Flash (`gemini-3-flash-preview`) - Ultra-fast, high-capability next-gen model
- Gemini 2.5 Flash Lite (`gemini-2.5-flash-lite`) - Lowest latency and cost
- - Gemini 2.0 Flash (`gemini-2.0-flash`) - Fast, long-context option
- **Local**: GGUF models via llama.cpp (Qwen, Llama, Mistral, GPT-OSS)
### 8. Model Registry Architecture
@@ -283,11 +282,11 @@ All AI model definitions are centralized in `src/models/modelRegistryData.json`
**Anthropic Integration**:
- Routes through IPC handler to avoid CORS issues in renderer process
- Uses main process for API calls with proper error handling
-- Model IDs use alias format (e.g., `claude-sonnet-4-5` not date-suffixed versions)
+- Model IDs use alias format (e.g., `claude-sonnet-4-6` not date-suffixed versions)
**Gemini Integration**:
- Direct API calls from renderer process
-- Increased token limits for Gemini 2.5 Pro (2000 minimum)
+- Increased token limits for Gemini 3.1 Pro (2000 minimum)
- Proper handling of thinking process in responses
- Error handling for MAX_TOKENS finish reason
diff --git a/src/models/modelRegistryData.json b/src/models/modelRegistryData.json
index 4fdf8faf5..c26154fd1 100644
--- a/src/models/modelRegistryData.json
+++ b/src/models/modelRegistryData.json
@@ -203,10 +203,10 @@
"name": "Anthropic",
"models": [
{
- "id": "claude-sonnet-4-5",
- "name": "Claude Sonnet 4.5",
+ "id": "claude-sonnet-4-6",
+ "name": "Claude Sonnet 4.6",
"description": "Balanced performance",
- "descriptionKey": "models.descriptions.cloud.anthropic_claude_sonnet_4_5"
+ "descriptionKey": "models.descriptions.cloud.anthropic_claude_sonnet_4_6"
},
{
"id": "claude-haiku-4-5",
@@ -215,10 +215,10 @@
"descriptionKey": "models.descriptions.cloud.anthropic_claude_haiku_4_5"
},
{
- "id": "claude-opus-4-5",
- "name": "Claude Opus 4.5",
+ "id": "claude-opus-4-6",
+ "name": "Claude Opus 4.6",
"description": "Most capable Claude model",
- "descriptionKey": "models.descriptions.cloud.anthropic_claude_opus_4_5"
+ "descriptionKey": "models.descriptions.cloud.anthropic_claude_opus_4_6"
}
]
},
@@ -227,10 +227,10 @@
"name": "Google Gemini",
"models": [
{
- "id": "gemini-3-pro-preview",
- "name": "Gemini 3 Pro",
+ "id": "gemini-3.1-pro-preview",
+ "name": "Gemini 3.1 Pro",
"description": "Next-gen flagship model for complex reasoning",
- "descriptionKey": "models.descriptions.cloud.gemini_gemini_3_pro_preview"
+ "descriptionKey": "models.descriptions.cloud.gemini_gemini_3_1_pro_preview"
},
{
"id": "gemini-3-flash-preview",