Voxta 141 Update: Faster STT & TTS + More!

Hey everyone!

We’re back with an experimental build that brings some major speed improvements by introducing out-of-process Python modules! If you’re self-hosting speech-to-text (STT) and text-to-speech (TTS), expect more parallelism and faster performance!

🔹 Faster & Smarter Speech Processing

• WhisperLive, Coqui XTTS, F5-TTS, and Kokoro now run out-of-process, reducing bottlenecks and boosting speed.

• WhisperLive can now run on a remote server, giving you more flexibility in your setup.

🔹 Action Inference System Upgrades

• Flattened activated actions – organize actions better and dynamically merge child actions based on conditions.

• New beforeSelectActionInference event – tweak upcoming action inference in scripts, giving you more control over actions.

🔹 UI & Experience Improvements

• Pick your audio input/output device directly in the browser.

• Simplified inspector with collapsible sections for easier navigation.

• Italicized roleplay text for a cleaner avatar view.

🔹 Stability & Fixes

• Llama.cpp improvements to prevent decoding errors in web searches.

• Coqui DeepSpeed disabled by default (waiting for Python 3.12 compatibility).

• Fixed multiple install issues (LlamaSharp, ffmpeg, and more).

• NAudio fixes – selected audio devices will now actually be used.

• Better scenario & character handling to avoid crashes and missing resources.

This build hasn’t been fully tested on Linux yet, so tread carefully! 🛠️

As always, your feedback is invaluable—try it out and let us know what you think!

How to install Voxta server app: https://youtu.be/1I9VkJ8tTlo
How to update Voxta server app: https://youtu.be/5aa7sducwoc