What is Tambourine Voice used for?

Tambourine Voice is an open-source AI voice dictation app that types cleaned-up speech at your cursor in any application, with configurable speech and language model providers. It is a good fit for dictating emails and documents by voice, and speaking prompts or notes into a code editor.

Is Tambourine Voice open source?

Yes. Tambourine Voice is open source under the AGPL-3.0 licence. Its source code is on GitHub at kstonekuan/tambourine-voice and is written mainly in Rust.

Is Tambourine Voice free?

Yes. Tambourine Voice is open source, so the software itself is free to use.

Can I self-host Tambourine Voice?

Yes. Tambourine Voice can be self-hosted on your own server or infrastructure; there is no official hosted version.

What is Tambourine Voice an alternative to?

Tambourine Voice is an open-source alternative to Wispr Flow. Other open-source alternatives to Wispr Flow include Handy.

Is Tambourine Voice actively maintained?

Yes. The most recent commit to Tambourine Voice was on 17 July 2026. The project has 388 stars on GitHub.

Tambourine Voice: open-source alternative to Wispr Flow

About Tambourine Voice

Tambourine is a personal voice interface that turns speech into text wherever your cursor is. You press a hotkey, speak, and the words are typed into emails, messages, documents, code editors or terminals without copy-pasting. It is positioned as an open-source alternative to Wispr Flow, Superwhisper and Willow, for people who want faster input than typing or who want to reduce keyboard strain.

Unlike raw transcription, it uses AI to tidy the text by removing filler words, adding punctuation and applying a personal dictionary for technical terms and names. You choose the speech-to-text provider from options such as Cartesia, Deepgram, AssemblyAI, Speechmatics, Azure, AWS, Google, Groq and OpenAI, and the language model from options such as Cerebras, OpenAI, Anthropic, Gemini, Groq and OpenRouter. It can also run fully locally with Whisper and Ollama. Prompts and formatting rules can be customized.

The app is cross-platform and built with Rust, Tauri, Python and TypeScript on the Pipecat framework. It is licensed under AGPL-3.0. A hosted service is listed as coming soon with a waitlist, so for now you run the server yourself.

Key features

Hotkey-triggered dictation into any app
AI cleanup of filler words and punctuation
Personal dictionary for technical terms
Choice of speech and language model providers
Fully local mode with Whisper and Ollama
Customizable formatting prompts

Good fit for

→Dictating emails and documents by voice
→Speaking prompts or notes into a code editor

Built with: Rust; Python; Tauri; TypeScript
Tags: voice-dictation; speech-to-text; ai; tauri; whisper; ollama; accessibility; productivity

Tambourine Voice: questions and answers

What is Tambourine Voice used for?: Tambourine Voice is an open-source AI voice dictation app that types cleaned-up speech at your cursor in any application, with configurable speech and language model providers. It is a good fit for dictating emails and documents by voice, and speaking prompts or notes into a code editor.
Is Tambourine Voice open source?: Yes. Tambourine Voice is open source under the AGPL-3.0 licence. Its source code is on GitHub at kstonekuan/tambourine-voice and is written mainly in Rust.
Is Tambourine Voice free?: Yes. Tambourine Voice is open source, so the software itself is free to use.
Can I self-host Tambourine Voice?: Yes. Tambourine Voice can be self-hosted on your own server or infrastructure; there is no official hosted version.
What is Tambourine Voice an alternative to?: Tambourine Voice is an open-source alternative to Wispr Flow. Other open-source alternatives to Wispr Flow include Handy.
Is Tambourine Voice actively maintained?: Yes. The most recent commit to Tambourine Voice was on 17 July 2026. The project has 388 stars on GitHub.