An open-source voice dictation tool that types your speech at the cursor in any application, powered by customizable AI transcription and formatting.
Tambourine is an open-source desktop application that acts as a personal voice interface for any software. It captures your speech via microphone, transcribes and formats it using AI, and automatically types the cleaned text wherever your cursor is located, eliminating the need for copy-pasting or app switching. It solves the problem of slow typing and context switching by enabling faster, hands-free text input across all applications.
Developers, writers, and knowledge workers who want to increase their text input speed, reduce repetitive strain, or need hands-free operation across various desktop applications like IDEs, email clients, and document editors.
Developers choose Tambourine for its full transparency, customization, and control over the AI pipeline, avoiding vendor lock-in. Its unique selling point is the ability to mix and match speech and language models, run entirely locally, and tailor formatting rules to specific applications and personal vocabulary.
Your personal voice interface for any app. Speak naturally and your words appear wherever your cursor is, with fully customizable AI voice dictation. Open source alternative to Wispr Flow.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Works in any desktop app where text input is possible, from email clients to code editors, eliminating app-switching as shown in the Windows Notepad demo.
Supports numerous STT and LLM providers, including free tiers like Cartesia and Cerebras, and local options like Whisper and Ollama for cost-effective or private use.
Allows editing formatting prompts, adding personal dictionaries, and enabling context-aware output tailored to specific applications, as detailed in the features section.
Fully open-source under AGPL-3.0, providing full control over the AI pipeline and avoiding vendor lock-in compared to proprietary tools like Wispr Flow.
Requires installing Rust, Node.js, Python, and configuring environment variables with API keys for STT and LLM providers, making initial deployment non-trivial.
Actively developed with warnings about breaking changes to code and configuration, unsuitable for environments needing long-term stability.
Linux support is marked with a warning (⚠️), and there's no mobile version, restricting usability across all devices.
tambourine-voice is an open-source alternative to the following products:
Willow is a digital twin platform for buildings and infrastructure that creates intelligent data models to optimize operations, maintenance, and sustainability.
Superwhisper is a tool or library related to speech recognition or audio processing, possibly built on OpenAI's Whisper model.
Wispr Flow is a workflow automation platform that helps businesses automate processes, integrate systems, and manage tasks through visual workflows.