@mastra/mcp-docs-server 0.0.0-error-handler-fix-20251020202607 → 0.0.0-execa-dynamic-import-20260304221256

package/.docs/raw/voice/overview.mdx

@@ -1,944 +0,0 @@
----
-title: Voice in Mastra | Mastra Docs
-description: Overview of voice capabilities in Mastra, including text-to-speech, speech-to-text, and real-time speech-to-speech interactions.
----
-
-import { Tabs } from "nextra/components";
-import { AudioPlayback } from "@/components/audio-playback";
-
-# Voice in Mastra
-
-Mastra's Voice system provides a unified interface for voice interactions, enabling text-to-speech (TTS), speech-to-text (STT), and real-time speech-to-speech (STS) capabilities in your applications.
-
-## Adding Voice to Agents
-
-To learn how to integrate voice capabilities into your agents, check out the [Adding Voice to Agents](../agents/adding-voice.mdx) documentation. This section covers how to use both single and multiple voice providers, as well as real-time interactions.
-
-```typescript
-import { Agent } from "@mastra/core/agent";
-import { openai } from "@ai-sdk/openai";
-import { OpenAIVoice } from "@mastra/voice-openai";
-
-// Initialize OpenAI voice for TTS
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions:
-    "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new OpenAIVoice(),
-});
-```
-
-You can then use the following voice capabilities:
-
-### Text to Speech (TTS)
-
-Turn your agent's responses into natural-sounding speech using Mastra's TTS capabilities.
-Choose from multiple providers like OpenAI, ElevenLabs, and more.
-
-For detailed configuration options and advanced features, check out our [Text-to-Speech guide](./text-to-speech).
-
-{/*
-LLM CONTEXT: This Tabs component demonstrates Text-to-Speech (TTS) implementation across different voice providers.
-Each tab shows how to set up and use a specific TTS provider (OpenAI, Azure, ElevenLabs, etc.) with Mastra agents.
-The tabs help users compare different TTS providers and choose the one that best fits their needs.
-Each tab includes complete code examples showing agent setup, text generation, and audio playback.
-The providers include OpenAI, Azure, ElevenLabs, PlayAI, Google, Cloudflare, Deepgram, Speechify, Sarvam, and Murf.
-*/}
-
-<Tabs items={["OpenAI", "Azure", "ElevenLabs", "PlayAI", "Google", "Cloudflare", "Deepgram", "Speechify", "Sarvam", "Murf"]}>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { OpenAIVoice } from "@mastra/voice-openai";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new OpenAIVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-speaker: "default", // Optional: specify a speaker
-responseFormat: "wav", // Optional: specify a response format
-});
-
-playAudio(audioStream);
-
-````
-
-Visit the [OpenAI Voice Reference](/reference/voice/openai) for more information on the OpenAI voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { AzureVoice } from "@mastra/voice-azure";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new AzureVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-  speaker: "en-US-JennyNeural", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-````
-
-Visit the [Azure Voice Reference](/reference/voice/azure) for more information on the Azure voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { ElevenLabsVoice } from "@mastra/voice-elevenlabs";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new ElevenLabsVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-speaker: "default", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-
-````
-
-Visit the [ElevenLabs Voice Reference](/reference/voice/elevenlabs) for more information on the ElevenLabs voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { PlayAIVoice } from "@mastra/voice-playai";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new PlayAIVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-  speaker: "default", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-````
-
-Visit the [PlayAI Voice Reference](/reference/voice/playai) for more information on the PlayAI voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { GoogleVoice } from "@mastra/voice-google";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new GoogleVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-speaker: "en-US-Studio-O", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-
-````
-
-Visit the [Google Voice Reference](/reference/voice/google) for more information on the Google voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { CloudflareVoice } from "@mastra/voice-cloudflare";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new CloudflareVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-  speaker: "default", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-````
-
-Visit the [Cloudflare Voice Reference](/reference/voice/cloudflare) for more information on the Cloudflare voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { DeepgramVoice } from "@mastra/voice-deepgram";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new DeepgramVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-speaker: "aura-english-us", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-
-````
-
-Visit the [Deepgram Voice Reference](/reference/voice/deepgram) for more information on the Deepgram voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { SpeechifyVoice } from "@mastra/voice-speechify";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new SpeechifyVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-  speaker: "matthew", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-````
-
-Visit the [Speechify Voice Reference](/reference/voice/speechify) for more information on the Speechify voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { SarvamVoice } from "@mastra/voice-sarvam";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new SarvamVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-speaker: "default", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-
-````
-
-Visit the [Sarvam Voice Reference](/reference/voice/sarvam) for more information on the Sarvam voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { MurfVoice } from "@mastra/voice-murf";
-import { playAudio } from "@mastra/node-audio";
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new MurfVoice(),
-});
-
-const { text } = await voiceAgent.generate('What color is the sky?');
-
-// Convert text to speech to an Audio Stream
-const audioStream = await voiceAgent.voice.speak(text, {
-  speaker: "default", // Optional: specify a speaker
-});
-
-playAudio(audioStream);
-````
-
-Visit the [Murf Voice Reference](/reference/voice/murf) for more information on the Murf voice provider.
-
-  </Tabs.Tab>
-</Tabs>
-
-### Speech to Text (STT)
-
-Transcribe spoken content using various providers like OpenAI, ElevenLabs, and more. For detailed configuration options and more, check out [Speech to Text](./speech-to-text).
-
-You can download a sample audio file from [here](https://github.com/mastra-ai/realtime-voice-demo/raw/refs/heads/main/how_can_i_help_you.mp3).
-
-<br />
-<AudioPlayback audio="https://github.com/mastra-ai/realtime-voice-demo/raw/refs/heads/main/how_can_i_help_you.mp3" />
-
-{/*
-LLM CONTEXT: This Tabs component demonstrates Speech-to-Text (STT) implementation across different voice providers.
-Each tab shows how to set up and use a specific STT provider for transcribing audio to text.
-The tabs help users understand how to implement speech recognition with different providers.
-Each tab includes code examples showing audio file handling, transcription, and response generation.
-*/}
-
-<Tabs items={["OpenAI", "Azure", "ElevenLabs", "Google", "Cloudflare", "Deepgram", "Sarvam"]}>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { OpenAIVoice } from "@mastra/voice-openai";
-import { createReadStream } from 'fs';
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new OpenAIVoice(),
-});
-
-// Use an audio file from a URL
-const audioStream = await createReadStream("./how_can_i_help_you.mp3");
-
-// Convert audio to text
-const transcript = await voiceAgent.voice.listen(audioStream);
-console.log(`User said: ${transcript}`);
-
-// Generate a response based on the transcript
-const { text } = await voiceAgent.generate(transcript);
-
-````
-
-Visit the [OpenAI Voice Reference](/reference/voice/openai) for more information on the OpenAI voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { createReadStream } from 'fs';
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { AzureVoice } from "@mastra/voice-azure";
-import { createReadStream } from 'fs';
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new AzureVoice(),
-});
-
-// Use an audio file from a URL
-const audioStream = await createReadStream("./how_can_i_help_you.mp3");
-
-// Convert audio to text
-const transcript = await voiceAgent.voice.listen(audioStream);
-console.log(`User said: ${transcript}`);
-
-// Generate a response based on the transcript
-const { text } = await voiceAgent.generate(transcript);
-````
-
-Visit the [Azure Voice Reference](/reference/voice/azure) for more information on the Azure voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { ElevenLabsVoice } from "@mastra/voice-elevenlabs";
-import { createReadStream } from 'fs';
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new ElevenLabsVoice(),
-});
-
-// Use an audio file from a URL
-const audioStream = await createReadStream("./how_can_i_help_you.mp3");
-
-// Convert audio to text
-const transcript = await voiceAgent.voice.listen(audioStream);
-console.log(`User said: ${transcript}`);
-
-// Generate a response based on the transcript
-const { text } = await voiceAgent.generate(transcript);
-
-````
-
-Visit the [ElevenLabs Voice Reference](/reference/voice/elevenlabs) for more information on the ElevenLabs voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { GoogleVoice } from "@mastra/voice-google";
-import { createReadStream } from 'fs';
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new GoogleVoice(),
-});
-
-// Use an audio file from a URL
-const audioStream = await createReadStream("./how_can_i_help_you.mp3");
-
-// Convert audio to text
-const transcript = await voiceAgent.voice.listen(audioStream);
-console.log(`User said: ${transcript}`);
-
-// Generate a response based on the transcript
-const { text } = await voiceAgent.generate(transcript);
-````
-
-Visit the [Google Voice Reference](/reference/voice/google) for more information on the Google voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { CloudflareVoice } from "@mastra/voice-cloudflare";
-import { createReadStream } from 'fs';
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new CloudflareVoice(),
-});
-
-// Use an audio file from a URL
-const audioStream = await createReadStream("./how_can_i_help_you.mp3");
-
-// Convert audio to text
-const transcript = await voiceAgent.voice.listen(audioStream);
-console.log(`User said: ${transcript}`);
-
-// Generate a response based on the transcript
-const { text } = await voiceAgent.generate(transcript);
-
-````
-
-Visit the [Cloudflare Voice Reference](/reference/voice/cloudflare) for more information on the Cloudflare voice provider.
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { DeepgramVoice } from "@mastra/voice-deepgram";
-import { createReadStream } from 'fs';
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new DeepgramVoice(),
-});
-
-// Use an audio file from a URL
-const audioStream = await createReadStream("./how_can_i_help_you.mp3");
-
-// Convert audio to text
-const transcript = await voiceAgent.voice.listen(audioStream);
-console.log(`User said: ${transcript}`);
-
-// Generate a response based on the transcript
-const { text } = await voiceAgent.generate(transcript);
-````
-
-Visit the [Deepgram Voice Reference](/reference/voice/deepgram) for more information on the Deepgram voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { SarvamVoice } from "@mastra/voice-sarvam";
-import { createReadStream } from 'fs';
-
-const voiceAgent = new Agent({
-name: "Voice Agent",
-instructions: "You are a voice assistant that can help users with their tasks.",
-model: openai("gpt-4o"),
-voice: new SarvamVoice(),
-});
-
-// Use an audio file from a URL
-const audioStream = await createReadStream("./how_can_i_help_you.mp3");
-
-// Convert audio to text
-const transcript = await voiceAgent.voice.listen(audioStream);
-console.log(`User said: ${transcript}`);
-
-// Generate a response based on the transcript
-const { text } = await voiceAgent.generate(transcript);
-
-````
-
-Visit the [Sarvam Voice Reference](/reference/voice/sarvam) for more information on the Sarvam voice provider.
-  </Tabs.Tab>
-</Tabs>
-
-### Speech to Speech (STS)
-
-Create conversational experiences with speech-to-speech capabilities. The unified API enables real-time voice interactions between users and AI agents.
-For detailed configuration options and advanced features, check out [Speech to Speech](./speech-to-speech).
-
-{/*
-  LLM CONTEXT: This Tabs component demonstrates Speech-to-Speech (STS) implementation for real-time voice interactions.
-  Currently only shows OpenAI's realtime voice implementation for bidirectional voice conversations.
-  The tab shows how to set up real-time voice communication with event handling for audio responses.
-  This enables conversational AI experiences with continuous audio streaming.
-*/}
-<Tabs items={["OpenAI", "Google Gemini Live"]}>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { playAudio, getMicrophoneStream } from '@mastra/node-audio';
-import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new OpenAIRealtimeVoice(),
-});
-
-// Listen for agent audio responses
-voiceAgent.voice.on('speaker', ({ audio }) => {
-  playAudio(audio);
-});
-
-// Initiate the conversation
-await voiceAgent.voice.speak('How can I help you today?');
-
-// Send continuous audio from the microphone
-const micStream = getMicrophoneStream();
-await voiceAgent.voice.send(micStream);
-````
-
-Visit the [OpenAI Voice Reference](/reference/voice/openai-realtime) for more information on the OpenAI voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-import { Agent } from '@mastra/core/agent';
-import { openai } from '@ai-sdk/openai';
-import { playAudio, getMicrophoneStream } from '@mastra/node-audio';
-import { GeminiLiveVoice } from "@mastra/voice-google-gemini-live";
-
-const voiceAgent = new Agent({
-  name: "Voice Agent",
-  instructions: "You are a voice assistant that can help users with their tasks.",
-  model: openai("gpt-4o"),
-  voice: new GeminiLiveVoice({
-    // Live API mode
-    apiKey: process.env.GOOGLE_API_KEY,
-    model: 'gemini-2.0-flash-exp',
-    speaker: 'Puck',
-    debug: true,
-    // Vertex AI alternative:
-    // vertexAI: true,
-    // project: 'your-gcp-project',
-    // location: 'us-central1',
-    // serviceAccountKeyFile: '/path/to/service-account.json',
-  }),
-});
-
-// Connect before using speak/send
-await voiceAgent.voice.connect();
-
-// Listen for agent audio responses
-voiceAgent.voice.on('speaker', ({ audio }) => {
-  playAudio(audio);
-});
-
-// Listen for text responses and transcriptions
-voiceAgent.voice.on('writing', ({ text, role }) => {
-  console.log(`${role}: ${text}`);
-});
-
-// Initiate the conversation
-await voiceAgent.voice.speak('How can I help you today?');
-
-// Send continuous audio from the microphone
-const micStream = getMicrophoneStream();
-await voiceAgent.voice.send(micStream);
-```
-
-Visit the [Google Gemini Live Reference](/reference/voice/google-gemini-live) for more information on the Google Gemini Live voice provider.
-
-  </Tabs.Tab>
-</Tabs>
-
-## Voice Configuration
-
-Each voice provider can be configured with different models and options. Below are the detailed configuration options for all supported providers:
-
-{/*
-LLM CONTEXT: This Tabs component shows detailed configuration options for all supported voice providers.
-Each tab demonstrates how to configure a specific voice provider with all available options and settings.
-The tabs help users understand the full configuration capabilities of each provider including models, languages, and advanced settings.
-Each tab shows both speech and listening model configurations where applicable.
-*/}
-
-<Tabs items={["OpenAI", "Azure", "ElevenLabs", "PlayAI", "Google", "Cloudflare", "Deepgram", "Speechify", "Sarvam", "Murf", "OpenAI Realtime", "Google Gemini Live"]}>
-  <Tabs.Tab>
-```typescript
-// OpenAI Voice Configuration
-const voice = new OpenAIVoice({
-  speechModel: {
-    name: "gpt-3.5-turbo", // Example model name
-    apiKey: process.env.OPENAI_API_KEY,
-    language: "en-US", // Language code
-    voiceType: "neural", // Type of voice model
-  },
-  listeningModel: {
-    name: "whisper-1", // Example model name
-    apiKey: process.env.OPENAI_API_KEY,
-    language: "en-US", // Language code
-    format: "wav", // Audio format
-  },
-  speaker: "alloy", // Example speaker name
-});
-```
-
-Visit the [OpenAI Voice Reference](/reference/voice/openai) for more information on the OpenAI voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Azure Voice Configuration
-const voice = new AzureVoice({
-  speechModel: {
-    name: "en-US-JennyNeural", // Example model name
-    apiKey: process.env.AZURE_SPEECH_KEY,
-    region: process.env.AZURE_SPEECH_REGION,
-    language: "en-US", // Language code
-    style: "cheerful", // Voice style
-    pitch: "+0Hz", // Pitch adjustment
-    rate: "1.0", // Speech rate
-  },
-  listeningModel: {
-    name: "en-US", // Example model name
-    apiKey: process.env.AZURE_SPEECH_KEY,
-    region: process.env.AZURE_SPEECH_REGION,
-    format: "simple", // Output format
-  },
-});
-```
-
-Visit the [Azure Voice Reference](/reference/voice/azure) for more information on the Azure voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// ElevenLabs Voice Configuration
-const voice = new ElevenLabsVoice({
-  speechModel: {
-    voiceId: "your-voice-id", // Example voice ID
-    model: "eleven_multilingual_v2", // Example model name
-    apiKey: process.env.ELEVENLABS_API_KEY,
-    language: "en", // Language code
-    emotion: "neutral", // Emotion setting
-  },
-  // ElevenLabs may not have a separate listening model
-});
-```
-
-Visit the [ElevenLabs Voice Reference](/reference/voice/elevenlabs) for more information on the ElevenLabs voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// PlayAI Voice Configuration
-const voice = new PlayAIVoice({
-  speechModel: {
-    name: "playai-voice", // Example model name
-    speaker: "emma", // Example speaker name
-    apiKey: process.env.PLAYAI_API_KEY,
-    language: "en-US", // Language code
-    speed: 1.0, // Speech speed
-  },
-  // PlayAI may not have a separate listening model
-});
-```
-
-Visit the [PlayAI Voice Reference](/reference/voice/playai) for more information on the PlayAI voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Google Voice Configuration
-const voice = new GoogleVoice({
-  speechModel: {
-    name: "en-US-Studio-O", // Example model name
-    apiKey: process.env.GOOGLE_API_KEY,
-    languageCode: "en-US", // Language code
-    gender: "FEMALE", // Voice gender
-    speakingRate: 1.0, // Speaking rate
-  },
-  listeningModel: {
-    name: "en-US", // Example model name
-    sampleRateHertz: 16000, // Sample rate
-  },
-});
-```
-
-Visit the [Google Voice Reference](/reference/voice/google) for more information on the Google voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Cloudflare Voice Configuration
-const voice = new CloudflareVoice({
-  speechModel: {
-    name: "cloudflare-voice", // Example model name
-    accountId: process.env.CLOUDFLARE_ACCOUNT_ID,
-    apiToken: process.env.CLOUDFLARE_API_TOKEN,
-    language: "en-US", // Language code
-    format: "mp3", // Audio format
-  },
-  // Cloudflare may not have a separate listening model
-});
-```
-
-Visit the [Cloudflare Voice Reference](/reference/voice/cloudflare) for more information on the Cloudflare voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Deepgram Voice Configuration
-const voice = new DeepgramVoice({
-  speechModel: {
-    name: "nova-2", // Example model name
-    speaker: "aura-english-us", // Example speaker name
-    apiKey: process.env.DEEPGRAM_API_KEY,
-    language: "en-US", // Language code
-    tone: "formal", // Tone setting
-  },
-  listeningModel: {
-    name: "nova-2", // Example model name
-    format: "flac", // Audio format
-  },
-});
-```
-
-Visit the [Deepgram Voice Reference](/reference/voice/deepgram) for more information on the Deepgram voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Speechify Voice Configuration
-const voice = new SpeechifyVoice({
-  speechModel: {
-    name: "speechify-voice", // Example model name
-    speaker: "matthew", // Example speaker name
-    apiKey: process.env.SPEECHIFY_API_KEY,
-    language: "en-US", // Language code
-    speed: 1.0, // Speech speed
-  },
-  // Speechify may not have a separate listening model
-});
-```
-
-Visit the [Speechify Voice Reference](/reference/voice/speechify) for more information on the Speechify voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Sarvam Voice Configuration
-const voice = new SarvamVoice({
-  speechModel: {
-    name: "sarvam-voice", // Example model name
-    apiKey: process.env.SARVAM_API_KEY,
-    language: "en-IN", // Language code
-    style: "conversational", // Style setting
-  },
-  // Sarvam may not have a separate listening model
-});
-```
-
-Visit the [Sarvam Voice Reference](/reference/voice/sarvam) for more information on the Sarvam voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Murf Voice Configuration
-const voice = new MurfVoice({
-  speechModel: {
-    name: "murf-voice", // Example model name
-    apiKey: process.env.MURF_API_KEY,
-    language: "en-US", // Language code
-    emotion: "happy", // Emotion setting
-  },
-  // Murf may not have a separate listening model
-});
-```
-
-Visit the [Murf Voice Reference](/reference/voice/murf) for more information on the Murf voice provider.
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// OpenAI Realtime Voice Configuration
-const voice = new OpenAIRealtimeVoice({
-  speechModel: {
-    name: "gpt-3.5-turbo", // Example model name
-    apiKey: process.env.OPENAI_API_KEY,
-    language: "en-US", // Language code
-  },
-  listeningModel: {
-    name: "whisper-1", // Example model name
-    apiKey: process.env.OPENAI_API_KEY,
-    format: "ogg", // Audio format
-  },
-  speaker: "alloy", // Example speaker name
-});
-```
-
-For more information on the OpenAI Realtime voice provider, refer to the [OpenAI Realtime Voice Reference](/reference/voice/openai-realtime).
-
-  </Tabs.Tab>
-  <Tabs.Tab>
-```typescript
-// Google Gemini Live Voice Configuration
-const voice = new GeminiLiveVoice({
-  speechModel: {
-    name: "gemini-2.0-flash-exp", // Example model name
-    apiKey: process.env.GOOGLE_API_KEY,
-  },
-  speaker: "Puck", // Example speaker name
-  // Google Gemini Live is a realtime bidirectional API without separate speech and listening models
-});
-```
-
-Visit the [Google Gemini Live Reference](/reference/voice/google-gemini-live) for more information on the Google Gemini Live voice provider.
-
-  </Tabs.Tab>
-</Tabs>
-
-### Using Multiple Voice Providers
-
-This example demonstrates how to create and use two different voice providers in Mastra: OpenAI for speech-to-text (STT) and PlayAI for text-to-speech (TTS).
-
-Start by creating instances of the voice providers with any necessary configuration.
-
-```typescript
-import { OpenAIVoice } from "@mastra/voice-openai";
-import { PlayAIVoice } from "@mastra/voice-playai";
-import { CompositeVoice } from "@mastra/core/voice";
-import { playAudio, getMicrophoneStream } from "@mastra/node-audio";
-
-// Initialize OpenAI voice for STT
-const input = new OpenAIVoice({
-  listeningModel: {
-    name: "whisper-1",
-    apiKey: process.env.OPENAI_API_KEY,
-  },
-});
-
-// Initialize PlayAI voice for TTS
-const output = new PlayAIVoice({
-  speechModel: {
-    name: "playai-voice",
-    apiKey: process.env.PLAYAI_API_KEY,
-  },
-});
-
-// Combine the providers using CompositeVoice
-const voice = new CompositeVoice({
-  input,
-  output,
-});
-
-// Implement voice interactions using the combined voice provider
-const audioStream = getMicrophoneStream(); // Assume this function gets audio input
-const transcript = await voice.listen(audioStream);
-
-// Log the transcribed text
-console.log("Transcribed text:", transcript);
-
-// Convert text to speech
-const responseAudio = await voice.speak(`You said: ${transcript}`, {
-  speaker: "default", // Optional: specify a speaker,
-  responseFormat: "wav", // Optional: specify a response format
-});
-
-// Play the audio response
-playAudio(responseAudio);
-```
-
-For more information on the CompositeVoice, refer to the [CompositeVoice Reference](/reference/voice/composite-voice).
-
-## More Resources
-
-- [CompositeVoice](../../reference/voice/composite-voice.mdx)
-- [MastraVoice](../../reference/voice/mastra-voice.mdx)
-- [OpenAI Voice](../../reference/voice/openai.mdx)
-- [OpenAI Realtime Voice](../../reference/voice/openai-realtime.mdx)
-- [Azure Voice](../../reference/voice/azure.mdx)
-- [Google Voice](../../reference/voice/google.mdx)
-- [Google Gemini Live Voice](../../reference/voice/google-gemini-live.mdx)
-- [Deepgram Voice](../../reference/voice/deepgram.mdx)
-- [PlayAI Voice](../../reference/voice/playai.mdx)
-- [Voice Examples](../../examples/voice/text-to-speech.mdx)