VocoType
VocoType is an offline voice input method for Windows and macOS: hold a shortcut, speak, and the text lands in whatever box you are typing in. Speech recognition runs locally on the CPU, so it works without a network and audio never leaves the computer. It handles mixed Chinese and English with technical terms, filters filler words, can fix errors with optional AI cleanup, and supports custom replacement dictionaries. It can also transcribe audio and video files to text or SRT subtitles, and an MCP server lets Claude or Cursor call it locally. The site is in Chinese; downloads are free.
Updated
✨ Try AgentScout's free AI image generator →Good for: building voice agents, connecting tools with MCP, making videos, running agents locally
Use cases
About VocoType
VocoType is listed in our voice category and is aimed at people who want a ready-to-use product. VocoType is an offline voice input method for Windows and macOS: hold a shortcut, speak, and the text lands in whatever box you are typing in. Speech recognition runs locally on the CPU, so it works without a network and audio never leaves the computer. It handles mixed Chinese and English with technical terms, filters filler words, can fix errors with optional AI cleanup, and supports custom replacement dictionaries. It can also transcribe audio and video files to text or SRT subtitles, and an MCP server lets Claude or Cursor call it locally. The site is in Chinese; downloads are free. Pricing, as the maker states it: Free. Maturity: Active. We last checked the official link on 2026-11-19.
VocoType at a glance
- Category: Voice
- Built for: People and teams who want a ready-to-use AI product
- Pricing: Free (as the maker states it)
- Official site: vocotype.com
- Listed on AgentScout: Nov 19, 2026
VocoType FAQ
What is VocoType?
VocoType is an offline voice input method for Windows and macOS: hold a shortcut, speak, and the text lands in whatever box you are typing in. Speech recognition runs locally on the CPU, so it works without a network and audio never leaves the computer. It handles mixed Chinese and English with technical terms, filters filler words, can fix errors with optional AI cleanup, and supports custom replacement dictionaries. It can also transcribe audio and video files to text or SRT subtitles, and an MCP server lets Claude or Cursor call it locally. The site is in Chinese; downloads are free.
How much does VocoType cost?
VocoType's pricing, as the maker states it: Free. Check the official site for current plans.
What are alternatives to VocoType?
Similar tools include Fish Audio, FunASR, yovoice, AITranscribe, Convai and Le Scribe Audio.
Facts from our link-checked listing and the official site. See something wrong? Suggest an edit.
VocoType ratings and reviews
Be the first to rate VocoType: tap 1 to 5 stars below. A written review is optional.
VocoType alternatives
Other voice tools in our directory. See all voice tools →
Fish Audio
Fish Audio is a voice AI platform for text to speech, voice cloning and speech to text, with a real-time API for voice agents. Its Drama 3 and S2 models take inline emotion and delivery tags such as whispering, laughing or pauses, it can clone a voice from a few seconds of audio, and its library has more than two million community voices for narration, characters, audiobooks and support agents. The Fish Speech models behind it are published on GitHub and Hugging Face.
FunASR
ModelScope's speech recognition toolkit for offline, streaming and edge ASR, with VAD, punctuation, speaker diarization and OpenAI-compatible/MCP serving.
yovoice
Local-first audio and music studio for macOS, Windows and Linux that runs text-to-speech, zero-shot voice cloning, emotional delivery controls, full songs with lyrics and General MIDI score arranging entirely on your own GPU or CPU via a native C++ engine, with a CLI, agent skill and API/MCP deployment option. Apache-2.0.
AITranscribe
AITranscribe converts Facebook videos and Reels, Instagram videos and uploaded audio into clean text transcripts and timestamped SRT or VTT subtitle files, with a translation mode and privacy-friendly processing after sign-in.
Convai
Conversational AI for virtual worlds: voice-enabled characters and agents that perceive, speak and act inside games and 3D scenes.
Le Scribe Audio
Le Scribe Audio is a 2-pass AI audio/video transcription platform with France OVHcloud storage, EU Vertex AI inference, and Word/SRT export; 60 minutes free.