Wiro - GPT Mini Realtime Voice Assistant - OpenAI Model icon

Wiro - GPT Mini Realtime Voice Assistant - OpenAI Model

GPT Mini Realtime enables low-latency, bidirectional streaming for voice and text. Build intera

Wiro - GPT Mini Realtime Voice Assistant - OpenAI Model

AI-generated

Overview

This node integrates with the Wiro API to provide a GPT Mini Realtime Voice Assistant using an OpenAI model. It enables low-latency, bidirectional streaming for voice and text interactions, allowing users to configure various voice and audio parameters for a customized AI assistant experience. Common scenarios include building interactive voice assistants, real-time transcription and response systems, and conversational AI applications with customizable voice characteristics.

Use Case Examples

  1. A customer support bot that listens to user queries in real-time and responds with a natural-sounding AI voice.
  2. An interactive storytelling assistant that uses expressive voice options to narrate stories dynamically.
  3. A transcription and voice response system for hands-free operation in smart home devices.

Properties

Name Meaning
Voice The voice of the AI assistant, selectable from various styles such as neutral, warm, calm, confident, energetic, mechanical, storytelling, natural, conversational, authoritative, knowledgeable, positive, and professional.
System Instructions Instructions that define the AI assistant's behavior and personality.
Transcription Model Model used for transcribing user speech to text, with options for fast lightweight, higher quality, or widely supported stable models.
Input Audio Format Audio format for user microphone input, with options for VoIP and best quality PCM formats.
Output Audio Format Audio format for AI voice output, with similar options as input audio format.
Input Audio Rate Sample rate for user microphone input, with options for 24kHz recommended or 8kHz phone quality.
Output Audio Rate Sample rate for AI voice output, with similar options as input audio rate.
Turn Detection Threshold Voice activity detection sensitivity; lower values make detection more sensitive, higher values less sensitive.
Silence Duration (Ms) Duration in milliseconds the user must be silent before the AI starts responding; default is 500ms.

Output

JSON

  • taskid - The unique identifier for the voice assistant task.
  • url - URL related to the completed task, possibly for accessing results or recordings.
  • status - Status of the task, indicating if it completed successfully or failed.

Dependencies

  • Wiro API

Troubleshooting

  • If the node throws an error indicating missing or invalid task ID or socket access token, verify that the Wiro API credentials (API key and secret) are correctly configured and valid.
  • Network issues or incorrect API endpoint may cause failure to initiate the voice assistant task; ensure internet connectivity and correct API URL.
  • Incorrect audio format or sample rate settings might cause audio processing errors; verify that input and output audio formats and rates are compatible with the user's audio hardware and the Wiro API specifications.

Links

Discussion