Whisper ASR Recorder (Portable)

Configuration

Whisper API Endpoint: Examples:
• Local: http://localhost:9100/asr
• OpenAI: https://api.openai.com/v1/audio/transcriptions
• Groq: https://api.groq.com/openai/v1/audio/transcriptions

Whisper API Format: • Local: For self-hosted Whisper (ahmetoner/whisper-asr-webservice)
• OpenAI/Groq: For cloud providers using OpenAI-compatible audio APIs

Whisper API Key (if required): Required for OpenAI and Groq Whisper endpoints

Whisper Model: • whisper-large-v3-turbo: Fast multilingual transcription (best for most uses)
• whisper-large-v3: Highest accuracy for multilingual content
• distil-whisper-large-v3-en: Fastest English-only model

API Format: • Ollama: Uses Ollama's specific API format
• OpenAI-compatible: Works with OpenAI, Groq, Anthropic, and most cloud LLMs
• Custom: For specialized API implementations

LLM API Endpoint: Examples:
• Ollama: http://localhost:11434/api/generate
• OpenAI: https://api.openai.com/v1/chat/completions
• Groq: https://api.groq.com/openai/v1/chat/completions
• Claude: https://api.anthropic.com/v1/messages

LLM Model: Examples:
• Ollama: qwen2.5-coder:14b, llama3:8b, openhermes
• OpenAI: gpt-4
• Groq: gemma2-9b-it, llama3-8b-8192, mixtral-8x7b-32768
• Claude: claude-3-opus-20240229, claude-3-sonnet-20240229

API Key (if required): Required for cloud LLM services. Not needed for local Ollama.

System Prompt: