AI BriefingVellium v1.1.0 Adds Local Voice Support
Key point
Vellium v1.1.0 released an update supporting local STT/TTS and automatic llama.cpp detection.
Details
The open-source, local-first AI chat and role-playing app Vellium released version v1.1.0, significantly improving local voice processing and model configuration experiences.
Enhanced Local Voice Interface
The new Live mode integrates microphone input, local or Whisper-compatible speech recognition, and streaming TTS. Whisper Large v3 Turbo Q5_0 is used for speech recognition, while TeraTTSv2 enables real-time English and Russian audio playback. The TTS process persists between responses, eliminating the need to reload the model each time.
Automated llama.cpp Configuration
llama.cpp environment setup has been simplified. Vellium automatically detects existing llama-server installations, GGUF models, and running local endpoints, configuring them as managed backends. It also supports macOS, Windows, and Linux, and can connect to OpenAI-compatible APIs, OpenRouter, LM Studio, Ollama, KoboldCpp, and others.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Ollaya Launches Local Runtime for Open-Source Decision Models with TypeSafe SDK CompatibilityJevper Released: A Jev Classification Wrapper for OpenAI-Compatible Models with Automatic Logprobs Detection