Frequently Asked Questions
Common questions and answers about WhisperApp
Can I use it offline?
Yes. WhisperApp runs entirely locally. Both transcription and LLM chat work without internet. Your audio data is never sent to external servers. Only the initial license activation requires a server connection — after that, all verification happens offline.
What file formats are supported?
MP3, WAV, M4A, FLAC, OGG, WMA, OPUS, AAC, MP4, MKV, AVI, WEBM, and more. The built-in audio conversion engine automatically converts files to the appropriate format, so you don't need to worry about compatibility.
Is a GPU required?
No. It works with CPU only. However, an NVIDIA GPU (CUDA), Intel GPU (OpenVINO), or Vulkan-compatible GPU significantly speeds up transcription. The app automatically detects your GPU and selects the optimal backend.
What are the trial limitations?
The 7-day trial gives you full access to all Pro features. A license purchase is required after the trial period ends. Note: internet connection is required at each startup during the trial (offline use is available after purchasing a license).
How many PCs can I use with one license?
One license key can be activated on up to 2 PCs (e.g., desktop + laptop). Re-registration to a different machine is allowed up to 3 times per year. The system is tolerant of hardware changes — if 2 or more of 5 hardware identifiers match, it's recognized as the same machine.
What happens after the update period ends?
The app continues to work after the update period (Standard: 6 months, Pro: 1 year). Bug fixes are provided indefinitely. However, feature updates to newer versions require a renewal fee (Standard ¥2,490 / Pro ¥3,990).
Is a refund available?
Since the 7-day free trial provides ample time to evaluate all features, refunds are generally not offered after purchase. Please see our refund policy for details.
Can I upgrade from Standard to Pro?
Yes. You can upgrade to Pro by paying the ¥3,000 difference. Your existing license key is carried over.
What's the difference between Standard and Pro?
Standard is a complete tool for turning your audio into text. It includes file transcription, mic recording, real-time transcription, and the full editor. Pro adds speaker diarization, system audio capture, YouTube/URL download, local LLM (summarize & chat), video subtitle generation, and smartphone integration.
What languages are supported?
Japanese, English, Chinese, Korean, French, German, Spanish, Russian, Portuguese, and Italian — 10 languages with auto-detection. The Whisper model itself supports 99 languages, but these 10 deliver the highest accuracy.
How accurate is speaker diarization?
Speaker diarization is powered by a dedicated engine. It supports automatic speaker detection as well as manual specification from 2 to 10 speakers. Results can be refined in the dedicated editor, where you can split, merge segments, and reassign speaker tags intuitively.
Is there an Android version?
Yes. WhisperApp for Android (free) is available. It supports standalone on-device transcription, plus integration with the Pro desktop app to leverage your PC's GPU for faster, higher-quality transcription.