GoWhisper

GoWhisper: The Privacy-First Local Audio Transcription Desktop App is a cross-platform desktop application designed for local, offline transcription of audio and video files. It emphasizes data privacy by keeping processing on the user’s machine in local mode, while offering optional API-mode processing for additional capabilities. The app supports a wide range of languages and audio/video formats, with a one-time purchase model to avoid recurring subscriptions.

---

How it Works

1. Choose language and model size. Supports up to 99 languages; larger models yield higher quality transcriptions.
2. Upload your file. Drag-and-drop or select MP3, M4A, WAV, MOV, and other common formats.
3. Export results. Output can be exported as SRT, TXT, VTT, or CSV.

The app is available in free and paid tiers, with a lifetime license option. Local mode keeps data on your computer; API mode sends data to OpenAI for processing.

---

Ideal Use Cases

• Researchers transcribing interviews and audio analyses.
• Podcasters converting episodes into blog posts or captions.
• Content creators generating accessible or SEO-friendly transcripts.
• Journalists and legal professionals transcribing interviews, depositions, or hearings.
• Small business owners documenting meetings or webinars.

---

How to Use GoWhisper

1. Install and run on macOS or Windows. Linux support planned as stability improves.
2. Select language and model size. Pick the transcription model that fits your needs.
3. Add your audio/video file. Drag-and-drop or browse to upload.
4. Export the transcript. Choose SRT, VTT, CSV, or TXT as required.

---

Pricing & Plans

• Free: Basic access with unlimited transcription in local mode.
• PRO (SUMMER SALE): $25 per license (lifetime), includes all AI models, transcription history, API transcription support, YouTube & podcast transcription, retranscribe feature, and future updates.
• Lifetime option: $50 per license (as listed in the roadmap). Note: Local mode ensures data stays on your computer; API mode processes data via OpenAI.

---

Roadmap & Next Planned Features

• AI summarization
• Q&A with transcription
• Autoupdate (Windows) and Linux compatibility improvements

---

Core Features

• Local/offline transcription on supported platforms (macOS, Windows; Linux planned)
• Choose language (up to 99) and model size for output quality
• Drag-and-drop or file upload for common formats (mp3, m4a, wav, mov, etc.)
• Export formats: SRT, TXT, VTT, CSV
• Privacy-first: local mode processes data on-device; API mode available for Cloud processing
• One-time purchase options: Free tier and lifetime licenses
• YouTube & Podcast transcription, retranscription features
• Multilingual transcription and future AI summarization enhancements