Skip to main content

OpenAI

Voice
Direct link to Voice

The OpenAIVoice class in Mastra provides text-to-speech and speech-to-text capabilities using OpenAI's models.

Usage example
Direct link to Usage example

import { OpenAIVoice } from '@mastra/voice-openai'

// Initialize with default configuration using environment variables
const voice = new OpenAIVoice()

// Or initialize with specific configuration
const voiceWithConfig = new OpenAIVoice({
  speechModel: {
    name: 'tts-1-hd',
    apiKey: 'your-openai-api-key',
  },
  listeningModel: {
    name: 'whisper-1',
    apiKey: 'your-openai-api-key',
  },
  speaker: 'alloy', // Default voice
})

// Convert text to speech
const audioStream = await voice.speak('Hello, how can I help you?', {
  speaker: 'nova', // Override default voice
  speed: 1.2, // Adjust speech speed
})

// Convert speech to text
const text = await voice.listen(audioStream, {
  filetype: 'mp3',
})

Configuration
Direct link to Configuration

Constructor options
Direct link to Constructor options

speechModel?:

OpenAIConfig
= { name: 'tts-1' }
Configuration for text-to-speech synthesis.
OpenAIConfig

name?:

'tts-1' | 'tts-1-hd' | 'whisper-1'
Model name. Use 'tts-1-hd' for higher quality audio.

apiKey?:

string
OpenAI API key. Falls back to OPENAI_API_KEY environment variable.

listeningModel?:

OpenAIConfig
= { name: 'whisper-1' }
Configuration for speech-to-text recognition.
OpenAIConfig

name?:

'tts-1' | 'tts-1-hd' | 'whisper-1'
Model name. Use 'tts-1-hd' for higher quality audio.

apiKey?:

string
OpenAI API key. Falls back to OPENAI_API_KEY environment variable.

speaker?:

OpenAIVoiceId
= 'alloy'
Default voice ID for speech synthesis.

Methods
Direct link to Methods

speak()
Direct link to speak

Converts text to speech using OpenAI's text-to-speech models.

input:

string | NodeJS.ReadableStream
Text or text stream to convert to speech.

options?:

Options
Configuration options.
Options

speaker?:

OpenAIVoiceId
Voice ID to use for speech synthesis.

speed?:

number
Speech speed multiplier.

Returns: Promise<NodeJS.ReadableStream>

listen()
Direct link to listen

Transcribes audio using OpenAI's Whisper model.

audioStream:

NodeJS.ReadableStream
Audio stream to transcribe.

options?:

Options
Configuration options.
Options

filetype?:

string
Audio format of the input stream.

Returns: Promise<string>

getSpeakers()
Direct link to getspeakers

Returns an array of available voice options, where each node contains:

voiceId:

string
Unique identifier for the voice

Notes
Direct link to Notes

  • API keys can be provided via constructor options or the OPENAI_API_KEY environment variable
  • The tts-1-hd model provides higher quality audio but may have slower processing times
  • Speech recognition supports multiple audio formats including mp3, wav, and webm

Realtime
Direct link to Realtime

The OpenAIRealtimeVoice class provides real-time voice interaction capabilities using OpenAI's WebSocket-based API. It supports real time speech to speech, voice activity detection, and event-based audio streaming.

Usage example
Direct link to Usage example

import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'

// Initialize with default configuration using environment variables
const voice = new OpenAIRealtimeVoice()

// Or initialize with specific configuration
const voiceWithConfig = new OpenAIRealtimeVoice({
  apiKey: 'your-openai-api-key',
  model: 'gpt-5.1-realtime-preview-2024-12-17',
  speaker: 'alloy', // Default voice
})

voiceWithConfig.updateSession({
  turn_detection: {
    type: 'server_vad',
    threshold: 0.6,
    silence_duration_ms: 1200,
  },
})

// Establish connection
await voice.connect()

// Set up event listeners
voice.on('speaker', ({ audio }) => {
  // Handle audio data (Int16Array) pcm format by default
  playAudio(audio)
})

voice.on('writing', ({ text, role }) => {
  // Handle transcribed text
  console.log(`${role}: ${text}`)
})

// Convert text to speech
await voice.speak('Hello, how can I help you today?', {
  speaker: 'echo', // Override default voice
})

// Process audio input
const microphoneStream = getMicrophoneStream()
await voice.send(microphoneStream)

// When done, disconnect
voice.connect()

Configuration
Direct link to Configuration

Constructor options
Direct link to Constructor options

model?:

string
= 'gpt-5.1-realtime-preview-2024-12-17'
The model ID to use for real-time voice interactions.

apiKey?:

string
OpenAI API key. Falls back to OPENAI_API_KEY environment variable.

speaker?:

string
= 'alloy'
Default voice ID for speech synthesis.

Voice Activity Detection (VAD) Configuration
Direct link to Voice Activity Detection (VAD) Configuration

type?:

string
= 'server_vad'
Type of VAD to use. Server-side VAD provides better accuracy.

threshold?:

number
= 0.5
Speech detection sensitivity (0.0-1.0).

prefix_padding_ms?:

number
= 1000
Milliseconds of audio to include before speech is detected.

silence_duration_ms?:

number
= 1000
Milliseconds of silence before ending a turn.

Methods
Direct link to Methods

connect()
Direct link to connect

Establishes a connection to the OpenAI Realtime service. Must be called before using speak, listen, or send functions.

returns:

Promise<void>
Promise that resolves when the connection is established.

speak()
Direct link to speak-1

Emits a speaking event using the configured voice model. Can accept either a string or a readable stream as input.

input:

string | NodeJS.ReadableStream
Text or text stream to convert to speech.

options?:

Options
Configuration options.
Options

speaker?:

string
Voice ID to use for this specific speech request.

Returns: Promise<void>

listen()
Direct link to listen-1

Processes audio input for speech recognition. Takes a readable stream of audio data and emits a 'listening' event with the transcribed text.

audioData:

NodeJS.ReadableStream
Audio stream to transcribe.

Returns: Promise<void>

send()
Direct link to send

Streams audio data in real-time to the OpenAI service for continuous audio streaming scenarios like live microphone input.

audioData:

NodeJS.ReadableStream
Audio stream to send to the service.

Returns: Promise<void>

updateConfig()
Direct link to updateconfig

Updates the session configuration for the voice instance. This can modify voice settings and turn detection. It can also modify other parameters.

sessionConfig:

Realtime.SessionConfig
New session configuration to apply.

Returns: void

addTools()
Direct link to addtools

Adds a set of tools to the voice instance. Tools allow the model to perform additional actions during conversations. When OpenAIRealtimeVoice is added to an Agent, any tools configured for the Agent will automatically be available to the voice interface.

tools?:

ToolsInput
Tools configuration to equip.

Returns: void

close()
Direct link to close

Disconnects from the OpenAI Realtime session and cleans up resources. Should be called when you're done with the voice instance.

Returns: void

getSpeakers()
Direct link to getspeakers-1

Returns a list of available voice speakers.

Returns: Promise<Array<{ voiceId: string; [key: string]: any }>>

on()
Direct link to on

Registers an event listener for voice events.

event:

string
Name of the event to listen for.

callback:

Function
Function to call when the event occurs.

Returns: void

off()
Direct link to off

Removes a previously registered event listener.

event:

string
Name of the event to stop listening to.

callback:

Function
The specific callback function to remove.

Returns: void

Events
Direct link to Events

The OpenAIRealtimeVoice class emits the following events:

speaking:

event
Emitted when audio data is received from the model. Callback receives { audio: Int16Array }.

writing:

event
Emitted when transcribed text is available. Callback receives { text: string, role: string }.

error:

event
Emitted when an error occurs. Callback receives the error object.

OpenAI Realtime Events
Direct link to OpenAI Realtime Events

You can also listen to OpenAI Realtime utility events by prefixing with 'openAIRealtime:':

openAIRealtime:conversation.created:

event
Emitted when a new conversation is created.

openAIRealtime:conversation.interrupted:

event
Emitted when a conversation is interrupted.

openAIRealtime:conversation.updated:

event
Emitted when a conversation is updated.

openAIRealtime:conversation.item.appended:

event
Emitted when an item is appended to the conversation.

openAIRealtime:conversation.item.completed:

event
Emitted when an item in the conversation is completed.

Available voices
Direct link to Available voices

The following voice options are available:

  • alloy: Neutral and balanced
  • ash: Clear and precise
  • ballad: Melodic and smooth
  • coral: Warm and friendly
  • echo: Resonant and deep
  • sage: Calm and thoughtful
  • shimmer: Bright and energetic
  • verse: Versatile and expressive

Notes
Direct link to Notes

  • API keys can be provided via constructor options or the OPENAI_API_KEY environment variable
  • The OpenAI Realtime Voice API uses WebSockets for real-time communication
  • Server-side Voice Activity Detection (VAD) provides better accuracy for speech detection
  • All audio data is processed as Int16Array format
  • The voice instance must be connected with connect() before using other methods
  • Always call close() when done to properly clean up resources
  • Memory management is handled by OpenAI Realtime API
On this page