System Audio Device Capture And Forwarding

via “audio input device management and multi-source support”

Tambourine is an open source, fully customizable voice dictation system that lets you control STT/ASR, LLM formatting, and prompts for inserting clean text into any app.I have been building this on the side for a few weeks. What motivated it was wanting a customizable version of Wispr Flow wher

Unique: Abstracts platform-specific audio APIs (PyAudio, CoreAudio, WASAPI) behind a unified Pipecat audio input interface, allowing developers to write device-agnostic code while supporting advanced features like virtual audio devices

vs others: More flexible than OS-native dictation APIs (which lock you to one microphone), while being simpler than building custom audio capture with raw ALSA/WASAPI calls

via “system-audio-device-capture-and-forwarding”

MCP App Server for live speech transcription

Unique: Integrates system audio device capture directly into MCP server lifecycle, eliminating need for separate recording tools or manual audio file management. Handles device enumeration and format negotiation transparently.

vs others: More seamless than piping external audio tools (ffmpeg, sox) because audio capture is built into the server process and integrated with MCP resource streaming.

via “dual-source audio capture and transcription”

Unique: Implements OS-level audio routing to capture both system and microphone streams simultaneously without requiring intermediate recording software or manual audio mixing, reducing workflow friction compared to tools that require separate capture setup

vs others: Captures dual audio sources natively where competitors like Otter.ai or Rev require manual file uploads or platform-specific integrations, reducing setup time for real-time accessibility workflows