Official documentation
FlashVoice/PRIVACY.md at main, GitHub
GitHub, harry0703/FlashVoice (maker's project repository), 2026
Read the originalRead on October 22, 2026
- What it is
- The privacy notice in the FlashVoice repository. It says microphone audio is captured and recognized on the device, and lists the AI providers that receive recognized text when AI proofreading is enabled.
- How much weight it carries
- The project's own privacy notice, read on the access date. It is a repository document, so it describes the open-source app's behavior rather than a hosted service.
Facts taken from this source
- FlashVoice's privacy notice says SenseVoice speech recognition runs on the device.
“Microphone and system audio are captured locally, and SenseVoice speech recognition runs on the device.” (Section 'Local processing and storage')
- FlashVoice's privacy notice says that when AI proofreading is enabled, recognized text and the prompt are sent to the selected provider.
“When AI proofreading is enabled, recognized text and the required prompt are sent to the selected OpenAI, Anthropic, Google Gemini, Ollama, or compatible endpoint.” (Section 'Network access')