Description
Transcribe and Summarize your recordings using your own AI providers (Bring Your Own Key), or local models that run completely offline on device.
**WHY THIS APP?**
One time purchase, with periodic updates with new features and improvements. Process locally or in the cloud with your own API keys (BYOK). No subscriptions, no account required. No middle-man servers. Complete privacy.
**PRIVACY FIRST**
No account needed. No Subscription. No tracking.
► No data collection in Offline mode. Your audio stays on your device in local mode.
► For Cloud mode, data is transmitted between your devices and the AI provider that you choose, there is no middle man server to process your audio.
**KEY FEATURES**
► Supports audio (MP3, M4A, WAV) and video (MP4, MOV, AVI) files - video audio is extracted automatically
► **100% Private Local Processing**
Your audio never leaves your device. Using the latest Whisper AI technology including Large V3 Turbo, transcribe with complete privacy and enhanced speed.
► **99+ Language Support with Easy Configuration**
Transcribe in over 99 languages with our new Language Configuration Panel on the home screen. Auto-detect or manually select for best accuracy. Keep original language or translate to English with optimized processing.
► **Customize your cloud AI providers and models**
Browse, select, or enter custom models for each cloud provider.
► **Smart AI Summaries & Chat**
Choose from 4 intelligent summary styles or engage with AI chat:
• Brief - Quick overview
• Detailed - Comprehensive analysis
• Bullet Points - Key takeaways
• Technical - Professional documentation
• Chat - Interactive Q&A about your transcripts
► **Advanced Model Selection**
Choose from multiple Whisper models (Tiny to Large V3 Turbo) and 11+ text generation models. Smart memory management shows which models work best on your device.
► **Flexible Processing**
• Local: Complete privacy, works offline
• Cloud: Lightning-fast processing
• Hybrid: Local transcription + cloud summaries
► **Background Processing**
Start a transcription and continue your day. Get notified when ready.
► **Universal Audio & Sharing**
Import from Voice Memos, Files, or record directly. Share audio from any app to instantly transcribe. Supports M4A, MP3, WAV, and more. Fixed audio playback through speaker for better presentation.
► Speaker Diarization for supported cloud AI providers and models
**PERFECT FOR**
• Professionals - Meeting notes and action items
• Students - Lecture transcripts and study notes
• Journalists - Interview recordings and quotes
• Researchers - Documentation and analysis
• International Teams - Multilingual meetings
• Content Creators - Repurpose audio content
**ADVANCED FEATURES**
► **Multiple AI Providers**
Choose from Whisper (local), OpenAI, Groq, or Anthropic. Optimize for speed, cost, or accuracy with expanded model options.
► **Language Intelligence**
• 99+ languages with enhanced translation
• Optimized language processing for better accuracy
• Easy language selection from home screen
• AI summaries adapt to your preference
► **Smart Model Management**
• Visual indicators for model compatibility
• Download any model with informed consent
• Automatic selection of best available model
• Memory-aware recommendations
► **Searchable History**
Find any quote or detail instantly with full-text search.
► **Export Anywhere**
Share transcripts via email, messages, or save to Files. Multiple format options.
► **iCloud Sync**
Keep your transcriptions, AI conversations, summaries, and audio files available on every device - work anywhere, pick up where you left off.
► **Smart Organization with Tabs and Folders**
Automatically categorize recordings by type (Meeting, Interview, etc.), mark favorites, and create custom folders to keep everything organized.
**SIMPLE PRICING**
One-time purchase. Unlimited transcriptions. No subscriptions. No Ads.
Nouveautés (v2.3)
► ElevenLabs Scribe v2 — New transcription model option with improved accuracy, better multilingual support, and enhanced handling of accented speech
► Improved speaker diarization reliability for long multi-speaker recordings
► Fireworks AI default model updated to Kimi K2 for improved text generation quality
► Added option to disable rating prompts in Settings > About