jxlpzqc/TMSpeech

Health v2 · maintenance only

Adoption not part of the score

1488 stars · 139 forks observed · 2026-10-19

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

TMSpeech is a Windows desktop application that captures system audio via WASAPI loopback and performs real-time Chinese speech-to-text, displaying results as karaoke-style subtitles. It also saves transcription history and meeting notes to files, and supports pluggable external recognizers via a command-line protocol.

Use cases

• show real-time captions for meeting audio on windows
• transcribe online meetings to text automatically
• catch up on a meeting after zoning out by reading recognition history
• generate meeting minutes saved by date
• use a custom speech recognition model as an external recognizer
• display live subtitles even with system sound muted

When to choose

• you need offline, low-CPU real-time Chinese speech captions on Windows
• you want to capture audio played by the computer rather than a microphone
• you want to plug in your own ASR model or command-line recognizer

When to avoid

• you need speech recognition on macOS or Linux
• you need English or other non-Chinese transcription out of the box
• you need cloud-based, speaker-diarized transcription services

Facets

application · maturity active

speech-recognition audio-processing gui speech-processing developer-tools windows windows real-time-captions meeting-transcription loopback-audio-capture chinese-asr sherpa-onnx subtitle-overlay desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jxlpzqc/TMSpeech")