Skip to content

The open-source AI voice studio. Clone, dictate, create.

Merge remote-tracking branch 'origin/main' into prep/pr-1012

jamiepine92774bbbaf12
diff --cc README.md
index aad3e531,f77ea4f2..b4db9a4f
--- a/README.md
+++ b/README.md
@@@ -65,9 -68,26 +68,26 @@@
<br/>
+ ## Built with Capy
+
+ <p align="center">
+ <a href="https://capy.ai?utm_source=voicebox&utm_medium=readme&utm_campaign=built-with-capy">
+ <picture>
+ <source media="(prefers-color-scheme: dark)" srcset=".github/assets/capy-wordmark-dark.svg" />
+ <img src=".github/assets/capy-wordmark-light.svg" alt="Capy" width="160" />
+ </picture>
+ </a>
+ </p>
+
+ Voicebox is built and maintained with [Capy](https://capy.ai?utm_source=voicebox&utm_medium=readme&utm_campaign=built-with-capy). A Capy Captain thread directs the project day to day, and its crew threads test, rebase, and review each contributor pull request on Linux and on a Mac Studio before Jamie merges it. Voicebox stays free and open source under the MIT license, with no splash screens, banners, or interruptions in the app.
+
+ **[Try Capy →](https://capy.ai?utm_source=voicebox&utm_medium=readme&utm_campaign=built-with-capy)** · [How Voicebox is built](https://voicebox.sh/built-with-capy)
+
+ ---
+
## What is Voicebox?
-Voicebox is a **local-first AI voice studio** — a free and open-source alternative to **ElevenLabs** and **WisprFlow** in one app. Clone voices from a few seconds of audio, generate speech in 23 languages across 7 TTS engines, dictate into any text field with a global hotkey, and give any MCP-aware AI agent a voice of your choosing.
+Voicebox is a **local-first AI voice studio** — a free and open-source alternative to **ElevenLabs** and **WisprFlow** in one app. Clone voices from a few seconds of audio, generate speech in 23 languages across 8 TTS engines, dictate into any text field with a global hotkey, and give any MCP-aware AI agent a voice of your choosing.
The two cloud incumbents sit on opposite halves of the voice I/O loop — ElevenLabs on output, WisprFlow on input. Voicebox does both, bridges them with a bundled local LLM for refinement and per-profile personas, and runs the whole thing on your machine.