CoFlu Settings

AI Settings

API Model:

API Key:

Cerebras Model:

ChatGPT Model:

Chutes Model:

Claude Model:

Deepinfra Model:

DeepSeek Model:

Google Model:

Grok Model:

Groq Model:

Hyperbolic Model:

MiniMax Model:

Ollama Model:

OpenRouter Model:

Perplexity Model:

Qwen Model:

SambaNova Model:

Together Model:

Enable Streaming Response

Enable High-cost Models

Enable External Models

OpenAI Compatibility

Receive Audio

Receive Images

Grounding with Google Search

Enable Thinking Output

Maximum Iterations: Maximum number of iterations for the "Generate" button

Appearance Settings

Enable Dark Mode

Enable Numbered Lines

Enable Wide Mode

Use Tokens Instead of Words

Enable Accessibility

Button Visibility Settings

Visible:

Hidden:

Comparison Settings

Enable Semantic Cleanup

Prompt Settings

Enable No BS Prompt

Enable No BS+ Prompt

Rendering Settings

Renderer:

Transcription Settings

Language:

API Model:

OpenAI Whisper Model:

Groq Whisper Model:

Auto-Split Large Audio

Translation Settings

Language:

Translation Batch Size (Speed Multiplier): Faster but more prone to failure (changing is recommended for top-tier API keys only)

Translation Batch RPM (Quota Slowdown): Maximum batches per minute (0 = unlimited, but it may cause errors)

Exponential Retry: Number of retry attempts for failed requests

Show Download Optimized Button