RocketWhisper Screenshots

AI-powered offline speech recognition and transcription software for Windows

RocketWhisper Main Window - Real-time speech recognition with transcription result

Main Window - Real-Time Speech Recognition

The main interface provides microphone input with real-time audio level monitoring, one-click recording with global hotkey support (Right Alt hold-to-talk), and instant transcription results powered by OpenAI Whisper (large-v3-turbo model). Recognized text can be automatically copied to clipboard or pasted into the active application.

RocketWhisper Settings - AI Processing with LLM provider selection

Settings - AI Processing (LLM Integration)

Supports multiple AI providers for intelligent text formatting: OpenAI (GPT-6.1 Sol / GPT-6 Luna), Anthropic (Claude), Groq (GPT-OSS - free tier), Google Gemini, and local LLM servers (Ollama, LM Studio). Use AI to automatically polish transcriptions into business emails, casual messages, summaries, or translations. Fully works offline with local LLM option.

RocketWhisper Batch Processing - Transcribe multiple audio files at once

Batch Processing - Transcribe Multiple Files

Process multiple audio and video files at once with drag-and-drop support. Supports WAV, MP3, M4A, FLAC, OGG, WMA, MP4, MKV, AVI, MOV, and more. Export results as plain text, SRT subtitles, or VTT subtitles. Ideal for meeting recordings, lecture transcription, and video subtitle generation.

← Back to Home