OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Chat & Assistants

Vocalis

Vocalis is an open-source speech-to-speech assistant with image analysis, built with a React frontend and FastAPI backend. It supports interruptible spoken conversations, live transcription, assistant-initiated greetings and follow-ups, and saved conversation sessions. Its repository describes connecting to local LLM and text-to-speech services through OpenAI-compatible endpoints.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vocalis — OpenViST project profile in Chat & Assistants.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Vocalis when you want an inspectable, self-hosted voice interface for interruptible conversation, image discussion or configurable local AI services.

Who it is for

  • People who want a voice-first assistant with natural interruption during spoken responses.
  • Developers self-hosting a speech interface and configuring local LLM or text-to-speech services.
  • Users who want to upload and discuss images as part of a multimodal conversation.

Documented uses

  • Hold a spoken conversation and interrupt the assistant while it is talking.
  • Upload an image and continue a conversation using visual understanding.
  • Save, retrieve and manage conversation sessions.
  • Personalize the assistant's name and system prompt through its preferences.
Before you choose

Requirements & limits

The repository is public and licensed under Apache-2.0. The README documents self-hosting on Windows and macOS/Linux.

  • Self-hosting prerequisites include Python 3.10 or newer, Node.js and npm.
  • The documented stack uses React 18, FastAPI, Python and Faster-Whisper.
  • The README describes CUDA acceleration with CPU fallback; CUDA support requires an optional PyTorch installation.
  • The repository describes OpenAI-compatible endpoints for local LLM and TTS services.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Vocalis from the repository

Install the documented frontend and backend dependencies and start both development servers.

Before you start

  • Python 3.10 or newer
  • Node.js and npm
  • The Vocalis repository

Steps

  1. Create and activate a Python virtual environment in the backend directory.

  2. Install backend dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  3. In the frontend directory, install dependencies with the command below.

    Documented command
    npm install

  4. Start the backend with the command below and the frontend with the command below.

    Documented command
    python -m backend.main
    Documented command
    npm run dev

Expected outcome

The documented manual setup starts the backend and frontend development servers.

Guide limitations

  • CUDA installation is a separate optional step; the README also describes CPU-only setup.
  • The repository instructions do not guarantee compatibility with every system or configured service.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Lex-au/Vocalis · Official homepage title · retained in its source language
How we review sourcesSuggest a correction