Tambourine vs Willow Voice
Both offer AI-powered voice dictation. Here's how they differ.
Quick Summary
Willow Voice is a VC-backed, polished voice dictation service with enterprise customers and a focus on accuracy. Tambourine is an open-source alternative that gives you full control: self-host on your infrastructure, choose from 10+ STT/LLM providers, customize formatting prompts, or run fully local with Whisper + Ollama.
Feature Comparison
| Feature | Tambourine | Willow Voice |
|---|---|---|
| Open Source | Yes (AGPL-3.0) | No |
| Self-Hostable | Yes (Docker available) | No |
| Choose STT Provider | 10+ options | Fixed |
| Choose LLM Provider | 10+ options | Fixed |
| Custom Prompts | Full control | Limited |
| Local/Offline Mode | Whisper + Ollama | Cloud-based |
| Windows Support | Yes | Yes |
| macOS Support | Yes | Yes |
| Enterprise Features | Self-managed | Team vocab, support |
| Auto-Learning Dictionary | Manual dictionary | Learns over time |
Why Choose Tambourine
Full Source Access
Audit the code, understand exactly what's happening with your voice data, contribute improvements.
Self-Host Everything
Run on your own infrastructure. Your voice data never leaves your network if you choose.
Choose Your Models
Pick from 10+ STT providers and LLM providers, or run fully local with Whisper + Ollama.
Customize Prompts
Full control over how your speech is formatted. Modify filler word handling, punctuation, and more.