--- title: "Network Transcription Over a Private LAN | Voicetypr" description: "Route Voicetypr dictation to a stronger computer on your private LAN. See how it works, what crosses the network, and the security limits to review." image: "https://voicetypr.com/voicetypr-og.png" canonical_url: "https://voicetypr.com/network-transcription" md_url: "https://voicetypr.com/network-transcription.md" last_updated: "2026-07-27" language: "en" --- [Voicetypr](https://voicetypr.com/)/Network transcription # Run the big models on your powerful machine, dictate from your light one Network transcription lets a light laptop route dictation to a powerful desktop on a trusted private LAN. The strong machine runs the downloaded local model; the recorded audio crosses your network to that machine rather than a hosted speech service. Last verified: July 27, 2026 Publisher and method: Voicetypr publishes this product explainer. The workflow and limits were checked against the public remote-transcription source and tests; this was not a network-security audit. Quick verdict Choose a local model on the current device when the simplest data boundary matters. Use LAN transcription when a trusted, stronger machine is worth sending recorded audio across your private network. Use neither as proof of a production air-gap or encrypted transport without validating the whole deployment. Stays on your LANNo internet requiredLocal models onlyShips in 2.0 [Start 3-day free trial](https://voicetypr.com/download)[See pricing](https://voicetypr.com/#pricing) How it works ## Three steps to dictate across your devices 1 ### Enable sharing on the strong machine On your powerful desktop, turn on network sharing. Voicetypr exposes its local transcription engine over your LAN through a built-in HTTP API. Add an optional password to lock the endpoint down. 2 ### Scan and select it on the light one On your laptop, open the Models tab and scan for LAN servers. Add the desktop, select it, and every dictation now routes to that machine over your own Wi-Fi. 3 ### Dictate like nothing changed Hold your hotkey and speak. Audio travels to the strong machine, the big model transcribes it, and the text lands in your focused field — same flow, more horsepower. What you get ## Built into the Models tab, with a network boundary to review - ✓ Any Voicetypr instance can expose its local transcription engine over the LAN through a built-in HTTP API. - ✓ In the Models tab you scan for, add, and select LAN servers — picking one routes all dictation to that machine. - ✓ An optional password protects the sharing endpoint, and you can see the real active-connection count. - ✓ Windows firewall detection flags blocked connections and walks you through the fix. - ✓ Only local models can be shared — cloud STT sources can't be routed over the network. Who it's for ## One strong machine, many places to dictate from ### Power users with a desktop and a laptop Keep the heavy Whisper or Parakeet models on the desktop that can actually run them, and dictate from the laptop you carry around the house. ### Weak or older laptops If your travel machine can't handle the larger local models, borrow the desktop's engine over the network instead of dropping to a smaller model. ### Privacy-conscious teams on a LAN Use one capable machine on a trusted private network, while recognizing that recorded audio crosses the LAN and the endpoint must be secured. Stays on your network ## Your audio stays between your own devices Network transcription happens between your Voicetypr machines: audio travels from the client to the selected LAN server and is transcribed there. Only downloaded Whisper or Parakeet models can be shared; the source rejects cloud speech providers. Because the public implementation uses a LAN HTTP endpoint with optional password authentication, use a password, keep the port off public networks, and treat both devices plus the LAN as part of your trusted boundary. ## Sources and verification - [Voicetypr remote-transcription source](https://github.com/ideaplexa/voicetypr/tree/main/src-tauri/src/remote) - [Voicetypr sharing commands and local-model guard](https://github.com/ideaplexa/voicetypr/blob/main/src-tauri/src/commands/remote.rs) - [Shipped local model guide](https://voicetypr.com/help/models) FAQ ## Network transcription questions ### Does my audio leave my network? In this mode, audio is sent from the client to the selected Voicetypr server on your LAN and transcribed there. The feature does not route the request through Voicetypr's servers, but you should still treat the LAN and server as part of your data boundary. ### Do I need an internet connection? The transcription request can stay on the private LAN after both devices and the model are set up. Licensing, model downloads, updates, and other optional network features are separate dependencies, so verify the complete workflow before relying on a disconnected deployment. ### How do I secure the sharing endpoint? Set a password on the sharing machine and use the feature only on a trusted private network. The public source exposes a LAN HTTP endpoint with optional password authentication; it does not document transport encryption, so do not expose the port to an untrusted network or the public internet. ### Can I share a cloud transcription source over the network? No. Only local models (Whisper, Parakeet) can be shared. Cloud STT sources can't be routed across devices — network transcription is local-engine to local-engine, by design. ### I'm on Windows and connections won't go through — what now? Voicetypr detects when the Windows firewall is blocking the sharing endpoint and shows you how to remediate it, so the light machine can reach the strong one. Related guides ## More on local, private dictation Compare the AI-tool workflow, the broader offline case, and how Voicetypr keeps your voice on your own hardware. [ai workflows Voice for AI agents Dictate prompts and context into AI tools — a natural fit once your strong machine is doing the transcribing. See the AI agents page →](https://voicetypr.com/voice-for-ai-agents) [offline by default Offline dictation The broader case for local transcription, for buyers who care most about keeping voice on their own hardware. See the offline guide →](https://voicetypr.com/best/offline-dictation) [privacy Voicetypr data-flow boundaries Separate local speech recognition from LAN audio, optional providers, licensing, telemetry, and destination-app storage. Review the data flow →](https://voicetypr.com/zero-knowledge) [full product boundary Privacy and data handling See the product-wide inventory beyond the LAN transcription step. Read the privacy page →](https://voicetypr.com/privacy) [stricter boundary Air-gapped workflow limits Understand why a LAN workflow and a fully disconnected deployment are not the same claim. Review the air-gap caveats →](https://voicetypr.com/air-gapped) ## Big-model dictation, anywhere on your network 3-day free trial. No credit card. Pay once from $39. Your voice stays on your own devices. [Start free trial](https://voicetypr.com/download)[Buy lifetime license](https://voicetypr.com/#pricing)