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

Swift

Swift is an open-source TypeScript Next.js web voice assistant that uses Groq for Whisper speech transcription and Llama 3 text generation, Cartesia Sonic for streamed speech synthesis, and voice activity detection to identify speech segments.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Swift — 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 Swift when a project needs a web-based voice interaction loop that connects speech detection, transcription, text generation and streamed audio output.

Who it is for

  • Developers building browser-based voice assistants.
  • Teams prototyping hands-free support or information-lookup interfaces.
  • Builders adapting a TypeScript and Next.js voice application for self-hosted or cloud deployment.

Documented uses

  • Transcribe spoken input with OpenAI Whisper through Groq.
  • Generate text responses with Meta Llama 3 through Groq.
  • Convert responses into streamed speech with Cartesia Sonic.
  • Detect speech segments with VAD.
  • Run the application locally or deploy it through Vercel.
Before you choose

Requirements & limits

The repository is public and identifies an MIT license. The documented setup requires Groq and Cartesia API keys; local development uses pnpm, and Vercel deployment is documented.

  • The application is written in TypeScript as a Next.js project.
  • Groq supplies both Whisper transcription and Llama 3 text generation.
  • Cartesia Sonic provides streamed speech synthesis to the frontend.
  • VAD handles speech-segment detection.
  • Vercel deployment is documented with GROQ_API_KEY and CARTESIA_API_KEY.

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 Swift for local development

Prepare the Swift Next.js application with its documented environment variables and dependencies.

Before you start

  • A cloned copy of the public Swift repository.
  • Groq and Cartesia API keys for the environment variables.
  • pnpm installed for dependency installation.

Steps

  1. Clone the repository.

  2. Copy .env.example to .env.local and fill in the environment variables.

  3. Run pnpm install to install dependencies.

  4. Run pnpm dev to start the development server.

Expected outcome

The documented local development server is started for the Swift application.

Guide limitations

  • The supplied instructions describe setup and starting the development server, but do not document a completed voice interaction or additional configuration.
  • The application uses Groq for Whisper transcription and Llama 3 text generation, and Cartesia Sonic for speech synthesis.
Documentation 1 ↗
Source-based practical guide

Deploy Swift through Vercel

Create a Vercel deployment using the repository’s documented deployment configuration.

Before you start

  • The public Swift repository.
  • A Groq API key.
  • A Cartesia API key.
  • A Vercel deployment.

Steps

  1. Use the repository’s Vercel deployment configuration.

  2. Provide GROQ_API_KEY and CARTESIA_API_KEY as the named environment variables.

  3. Complete the Vercel deployment flow.

Expected outcome

A Vercel deployment of the Swift web voice assistant is configured with the documented provider keys.

Guide limitations

  • The evidence verifies the Vercel deployment path and named variables but does not provide additional deployment settings or operational testing results.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
ai-ng/swift · Official homepage title · retained in its source language
How we review sourcesSuggest a correction