Daily Real-Time Voice Inference React Native SDK

RTVI-AI is an open standard for Real-Time Voice [and Video] Inference.

This library exports a VoiceClient that has the Daily transport associated.

Minimum OS/SDK versions

This package introduces some constraints on what OS/SDK versions your project can support:

• iOS: Deployment target >= 13
• Android: minSdkVersion >= 24

Installation

Install @pipecat-ai/react-native-daily-transport along with its peer dependencies:

npm i @pipecat-ai/react-native-daily-transport
npm i @daily-co/react-native-daily-js@^0.70.0
npm i @daily-co/react-native-webrtc@^118.0.3-daily.2
npm i @react-native-async-storage/async-storage@^1.23.1
npm i react-native-background-timer@^2.4.1
npm i react-native-get-random-values@^1.11.0

If you are using Expo, you will also need to add the following dependencies:

npm i @config-plugins/react-native-webrtc@^10.0.0
npm i @daily-co/[email protected]

All the details about Expo can be found here.

A full demo can be found here

Quick Start

Instantiate a VoiceClient instance, wire up the bot's audio, and start the conversation:

let voiceClient = new RTVIClient({
  transport: new RNDailyTransport(),
  params: {
    baseUrl: url,
    config: [
      {
        service: "tts",
        options: [
          { name: "voice", value: "79a125e8-cd45-4c13-8a67-188112f4dd22" },
        ],
      },
      {
        service: "llm",
        options: [
          { name: "model", value: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo" },
          {
            name: "initial_messages",
            value: [
              {
                role: "system",
                content:
                  "You are a assistant called ExampleBot. You can ask me anything. Keep responses brief and legible. Your responses will converted to audio. Please do not include any special characters in your response other than '!' or '?'. Start by briefly introducing yourself.",
              },
            ],
          },
          { name: "run_on_config", value: true },
        ],
      },
    ],
    requestData: {
      services: {
        llm: "together",
        tts: "cartesia",
      },
    },
    endpoints: {
      connect: "/start",
      action: "/action"
    }
  },
  enableMic: true,
  enableCam: false
})

await voiceClient.start()

References

• RTVI-AI overview.
• RTVI-AI reference docs.

Contributing

We are welcoming contributions to this project in form of issues and pull request. For questions about RTVI head over to the Pipecat discord server and check the #rtvi channel.