@mastra/voice-cloudflare 0.12.1 → 0.12.2

package/dist/docs/references/docs-agents-adding-voice.md

@@ -20,7 +20,7 @@ export const agent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: `You are a helpful assistant with both STT and TTS capabilities.`,
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice,
 })
 
@@ -109,7 +109,7 @@ export const agent = new Agent({
   id: 'speech-to-speech-agent',
   name: 'Speech-to-Speech Agent',
   instructions: `You are a helpful assistant with speech-to-speech capabilities.`,
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   tools: {
     // Tools configured on Agent are passed to voice provider
     search,
@@ -132,6 +132,37 @@ agent.voice.send(microphoneStream)
 agent.voice.close()
 ```
 
+### Per-session voice for concurrent sessions
+
+A static `voice` instance is shared across every request. For one-shot text-to-speech this is fine, but realtime and speech-to-speech providers store one WebSocket, one set of tools, and one request context per instance. If you deploy a single agent that handles several live sessions at once, a shared instance lets one session overwrite another session's tools, instructions, and request context.
+
+To give each session its own voice, provide `voice` as a resolver. Mastra runs the resolver on every `getVoice()` call and returns a fresh, session-owned instance:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
+
+export const agent = new Agent({
+  id: 'support-line',
+  name: 'Support Line',
+  instructions: ({ requestContext }) => `Help user ${requestContext.get('user')}.`,
+  model: 'openai/gpt-5.5',
+  voice: ({ requestContext }) => new OpenAIRealtimeVoice({ apiKey: requestContext.get('apiKey') }),
+})
+
+// Each concurrent session resolves its own voice instance
+const voice = await agent.getVoice({ requestContext })
+await voice.connect()
+```
+
+When you use a resolver:
+
+- Each call to `getVoice()` returns a new instance, so concurrent sessions never share state.
+- Mastra does not add tools or instructions to a resolver instance. Configure those inside the resolver or on the provider.
+- You own the lifecycle of the returned instance, so call `disconnect()` or `close()` when the session ends.
+
+The `agent.voice` getter has no request context, so it throws when `voice` is a resolver. Use `agent.getVoice({ requestContext })` instead.
+
 ### Event System
 
 The realtime voice provider emits several events you can listen for:
@@ -209,7 +240,7 @@ export const convertToText = async (input: string | NodeJS.ReadableStream): Prom
 export const hybridVoiceAgent = new Agent({
   id: 'hybrid-voice-agent',
   name: 'Hybrid Voice Agent',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   instructions: 'You can speak and listen using different providers.',
   voice: new CompositeVoice({
     input: new OpenAIVoice(),
@@ -221,7 +252,7 @@ export const unifiedVoiceAgent = new Agent({
   id: 'unified-voice-agent',
   name: 'Unified Voice Agent',
   instructions: 'You are an agent with both STT and TTS capabilities.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new OpenAIVoice(),
 })
 
@@ -263,7 +294,7 @@ export const agent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: `You are a helpful assistant with both STT and TTS capabilities.`,
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
 
   // Create a composite voice using OpenAI for listening and PlayAI for speaking
   voice: new CompositeVoice({
@@ -288,7 +319,7 @@ export const agent = new Agent({
   id: 'aisdk-voice-agent',
   name: 'AI SDK Voice Agent',
   instructions: `You are a helpful assistant with voice capabilities.`,
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
 
   // Pass AI SDK models directly to CompositeVoice
   voice: new CompositeVoice({
@@ -327,23 +358,24 @@ For the complete list of supported AI SDK providers and their capabilities:
 
 Mastra supports multiple voice providers for text-to-speech (TTS) and speech-to-text (STT) capabilities:
 
-| Provider        | Package                         | Features                  | Reference                                                          |
-| --------------- | ------------------------------- | ------------------------- | ------------------------------------------------------------------ |
-| OpenAI          | `@mastra/voice-openai`          | TTS, STT                  | [Documentation](https://mastra.ai/reference/voice/openai)          |
-| OpenAI Realtime | `@mastra/voice-openai-realtime` | Realtime speech-to-speech | [Documentation](https://mastra.ai/reference/voice/openai-realtime) |
-| ElevenLabs      | `@mastra/voice-elevenlabs`      | High-quality TTS          | [Documentation](https://mastra.ai/reference/voice/elevenlabs)      |
-| PlayAI          | `@mastra/voice-playai`          | TTS                       | [Documentation](https://mastra.ai/reference/voice/playai)          |
-| Google          | `@mastra/voice-google`          | TTS, STT                  | [Documentation](https://mastra.ai/reference/voice/google)          |
-| Deepgram        | `@mastra/voice-deepgram`        | STT                       | [Documentation](https://mastra.ai/reference/voice/deepgram)        |
-| Murf            | `@mastra/voice-murf`            | TTS                       | [Documentation](https://mastra.ai/reference/voice/murf)            |
-| Speechify       | `@mastra/voice-speechify`       | TTS                       | [Documentation](https://mastra.ai/reference/voice/speechify)       |
-| Sarvam          | `@mastra/voice-sarvam`          | TTS, STT                  | [Documentation](https://mastra.ai/reference/voice/sarvam)          |
-| Azure           | `@mastra/voice-azure`           | TTS, STT                  | [Documentation](https://mastra.ai/reference/voice/mastra-voice)    |
-| Cloudflare      | `@mastra/voice-cloudflare`      | TTS                       | [Documentation](https://mastra.ai/reference/voice/mastra-voice)    |
+| Provider        | Package                         | Features                                  | Reference                                                          |
+| --------------- | ------------------------------- | ----------------------------------------- | ------------------------------------------------------------------ |
+| OpenAI          | `@mastra/voice-openai`          | TTS, STT                                  | [Documentation](https://mastra.ai/reference/voice/openai)          |
+| OpenAI Realtime | `@mastra/voice-openai-realtime` | Realtime speech-to-speech                 | [Documentation](https://mastra.ai/reference/voice/openai-realtime) |
+| AWS Nova Sonic  | `@mastra/voice-aws-nova-sonic`  | Realtime speech-to-speech via AWS Bedrock | [Documentation](https://mastra.ai/reference/voice/aws-nova-sonic)  |
+| ElevenLabs      | `@mastra/voice-elevenlabs`      | High-quality TTS                          | [Documentation](https://mastra.ai/reference/voice/elevenlabs)      |
+| PlayAI          | `@mastra/voice-playai`          | TTS                                       | [Documentation](https://mastra.ai/reference/voice/playai)          |
+| Google          | `@mastra/voice-google`          | TTS, STT                                  | [Documentation](https://mastra.ai/reference/voice/google)          |
+| Deepgram        | `@mastra/voice-deepgram`        | STT                                       | [Documentation](https://mastra.ai/reference/voice/deepgram)        |
+| Murf            | `@mastra/voice-murf`            | TTS                                       | [Documentation](https://mastra.ai/reference/voice/murf)            |
+| Speechify       | `@mastra/voice-speechify`       | TTS                                       | [Documentation](https://mastra.ai/reference/voice/speechify)       |
+| Sarvam          | `@mastra/voice-sarvam`          | TTS, STT                                  | [Documentation](https://mastra.ai/reference/voice/sarvam)          |
+| Azure           | `@mastra/voice-azure`           | TTS, STT                                  | [Documentation](https://mastra.ai/reference/voice/mastra-voice)    |
+| Cloudflare      | `@mastra/voice-cloudflare`      | TTS                                       | [Documentation](https://mastra.ai/reference/voice/mastra-voice)    |
 
 ## Next steps
 
-- [Voice API Reference](https://mastra.ai/reference/voice/mastra-voice) - Detailed API documentation for voice capabilities
-- [Text to Speech Examples](https://github.com/mastra-ai/voice-examples/tree/main/text-to-speech) - Interactive story generator and other TTS implementations
-- [Speech to Text Examples](https://github.com/mastra-ai/voice-examples/tree/main/speech-to-text) - Voice memo app and other STT implementations
-- [Speech to Speech Examples](https://github.com/mastra-ai/voice-examples/tree/main/speech-to-speech) - Real-time voice conversation with call analysis
+- [Voice API Reference](https://mastra.ai/reference/voice/mastra-voice): Detailed API documentation for voice capabilities
+- [Text to Speech Examples](https://github.com/mastra-ai/voice-examples/tree/main/text-to-speech): Interactive story generator and other TTS implementations
+- [Speech to Text Examples](https://github.com/mastra-ai/voice-examples/tree/main/speech-to-text): Voice memo app and other STT implementations
+- [Speech to Speech Examples](https://github.com/mastra-ai/voice-examples/tree/main/speech-to-speech): Real-time voice conversation with call analysis

package/dist/docs/references/docs-voice-overview.md

@@ -16,7 +16,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new OpenAIVoice(),
 })
 ```
@@ -40,7 +40,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new OpenAIVoice(),
 })
 
@@ -68,7 +68,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new AzureVoice(),
 })
 
@@ -95,7 +95,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new ElevenLabsVoice(),
 })
 
@@ -122,7 +122,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new PlayAIVoice(),
 })
 
@@ -149,7 +149,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new GoogleVoice(),
 })
 
@@ -176,7 +176,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new CloudflareVoice(),
 })
 
@@ -203,7 +203,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new DeepgramVoice(),
 })
 
@@ -219,6 +219,33 @@ playAudio(audioStream)
 
 Visit the [Deepgram Voice Reference](https://mastra.ai/reference/voice/deepgram) for more information on the Deepgram voice provider.
 
+**Inworld**:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { InworldVoice } from '@mastra/voice-inworld'
+import { playAudio } from '@mastra/node-audio'
+
+const voiceAgent = new Agent({
+  id: 'voice-agent',
+  name: 'Voice Agent',
+  instructions: 'You are a voice assistant that can help users with their tasks.',
+  model: 'openai/gpt-5.5',
+  voice: new InworldVoice(),
+})
+
+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: 'Dennis', // Optional: specify a speaker
+})
+
+playAudio(audioStream)
+```
+
+Visit the [Inworld Voice Reference](https://mastra.ai/reference/voice/inworld) for more information on the Inworld voice provider.
+
 **Speechify**:
 
 ```typescript
@@ -230,7 +257,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new SpeechifyVoice(),
 })
 
@@ -257,7 +284,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new SarvamVoice(),
 })
 
@@ -265,7 +292,7 @@ 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
+  speaker: 'shubh', // Optional: specify a bulbul:v3 speaker
 })
 
 playAudio(audioStream)
@@ -284,7 +311,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new MurfVoice(),
 })
 
@@ -319,7 +346,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new OpenAIVoice(),
 })
 
@@ -348,7 +375,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new AzureVoice(),
 })
 
@@ -376,7 +403,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new ElevenLabsVoice(),
 })
 
@@ -404,7 +431,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new GoogleVoice(),
 })
 
@@ -432,7 +459,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new CloudflareVoice(),
 })
 
@@ -460,7 +487,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new DeepgramVoice(),
 })
 
@@ -477,6 +504,34 @@ const { text } = await voiceAgent.generate(transcript)
 
 Visit the [Deepgram Voice Reference](https://mastra.ai/reference/voice/deepgram) for more information on the Deepgram voice provider.
 
+**Inworld**:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { InworldVoice } from '@mastra/voice-inworld'
+import { createReadStream } from 'fs'
+
+const voiceAgent = new Agent({
+  id: 'voice-agent',
+  name: 'Voice Agent',
+  instructions: 'You are a voice assistant that can help users with their tasks.',
+  model: 'openai/gpt-5.5',
+  voice: new InworldVoice(),
+})
+
+// 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 [Inworld Voice Reference](https://mastra.ai/reference/voice/inworld) for more information on the Inworld voice provider.
+
 **Sarvam**:
 
 ```typescript
@@ -488,7 +543,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new SarvamVoice(),
 })
 
@@ -520,7 +575,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new OpenAIRealtimeVoice(),
 })
 
@@ -550,7 +605,7 @@ const voiceAgent = new Agent({
   id: 'voice-agent',
   name: 'Voice Agent',
   instructions: 'You are a voice assistant that can help users with their tasks.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice: new GeminiLiveVoice({
     // Live API mode
     apiKey: process.env.GOOGLE_API_KEY,
@@ -588,6 +643,134 @@ await voiceAgent.voice.send(micStream)
 
 Visit the [Google Gemini Live Reference](https://mastra.ai/reference/voice/google-gemini-live) for more information on the Google Gemini Live voice provider.
 
+**AWS Nova Sonic**:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
+import { NovaSonicVoice } from '@mastra/voice-aws-nova-sonic'
+
+const voiceAgent = new Agent({
+  id: 'voice-agent',
+  name: 'Voice Agent',
+  instructions: 'You are a voice assistant that can help users with their tasks.',
+  model: 'openai/gpt-5.5',
+  voice: new NovaSonicVoice({
+    region: 'us-east-1',
+    speaker: 'matthew',
+    // Static credentials are optional. The default AWS credential
+    // provider chain is used when none are passed.
+  }),
+})
+
+// Connect before using speak/send
+await voiceAgent.voice.connect()
+
+// Listen for assistant audio (Int16Array PCM)
+voiceAgent.voice.on('speaking', ({ audioData }) => {
+  if (audioData) playAudio(audioData)
+})
+
+// Listen for transcribed text
+voiceAgent.voice.on('writing', ({ text, role }) => {
+  console.log(`${role}: ${text}`)
+})
+
+// Initiate the conversation
+await voiceAgent.voice.speak('How can I help you today?')
+
+// Send continuous audio from the microphone
+const micStream = getMicrophoneStream()
+await voiceAgent.voice.send(micStream)
+```
+
+Visit the [AWS Nova Sonic Reference](https://mastra.ai/reference/voice/aws-nova-sonic) for more information on the AWS Nova Sonic voice provider.
+
+**Inworld Realtime**:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
+import { InworldRealtimeVoice } from '@mastra/voice-inworld'
+
+const voiceAgent = new Agent({
+  id: 'voice-agent',
+  name: 'Voice Agent',
+  instructions: 'You are a voice assistant that can help users with their tasks.',
+  model: 'openai/gpt-5.5',
+  voice: new InworldRealtimeVoice({
+    apiKey: process.env.INWORLD_API_KEY,
+    model: 'inworld/models/gemma-4-26b-a4b-it',
+    speaker: 'Sarah',
+  }),
+})
+
+// Connect before using speak/send
+await voiceAgent.voice.connect()
+
+// Listen for agent audio (PCM stream)
+voiceAgent.voice.on('speaker', stream => {
+  playAudio(stream)
+})
+
+// Listen for text responses and transcriptions
+voiceAgent.voice.on('writing', ({ text, role }) => {
+  console.log(`${role}: ${text}`)
+})
+
+// Initiate the conversation
+await voiceAgent.voice.speak('How can I help you today?')
+
+// Send continuous audio from the microphone
+const micStream = getMicrophoneStream()
+await voiceAgent.voice.send(micStream)
+```
+
+Visit the [Inworld Realtime Reference](https://mastra.ai/reference/voice/inworld-realtime) for more information on the Inworld Realtime voice provider.
+
+**xAI**:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
+import { XAIRealtimeVoice } from '@mastra/voice-xai-realtime'
+
+const voiceAgent = new Agent({
+  id: 'voice-agent',
+  name: 'Voice Agent',
+  instructions: 'You are a voice assistant that can help users with their tasks.',
+  model: 'xai/grok-4.3',
+  voice: new XAIRealtimeVoice({
+    apiKey: process.env.XAI_API_KEY,
+    model: 'grok-voice-think-fast-1.0',
+    speaker: 'eve',
+    turnDetection: { type: 'server_vad' },
+  }),
+})
+
+// Connect before using speak/send
+await voiceAgent.voice.connect()
+
+// Listen for agent audio responses
+voiceAgent.voice.on('speaker', audioStream => {
+  playAudio(audioStream)
+})
+
+// Listen for text responses and transcriptions
+voiceAgent.voice.on('writing', ({ text, role }) => {
+  console.log(`${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 [xAI Realtime Voice Reference](https://mastra.ai/reference/voice/xai-realtime) for more information on the xAI voice provider.
+
 ## Voice configuration
 
 Each voice provider can be configured with different models and options. Below are the detailed configuration options for all supported providers:
@@ -736,6 +919,34 @@ const voice = new DeepgramVoice({
 
 Visit the [Deepgram Voice Reference](https://mastra.ai/reference/voice/deepgram) for more information on the Deepgram voice provider.
 
+**Inworld**:
+
+```typescript
+// Inworld Voice Configuration
+const voice = new InworldVoice({
+  speechModel: {
+    name: 'inworld-tts-2',
+    apiKey: process.env.INWORLD_API_KEY,
+  },
+  listeningModel: {
+    name: 'groq/whisper-large-v3',
+    apiKey: process.env.INWORLD_API_KEY,
+  },
+  speaker: 'Dennis',
+  audioEncoding: 'MP3',
+  sampleRateHertz: 48000,
+  language: 'en-US',
+})
+
+// Per-call options: `deliveryMode` is honored only by `inworld-tts-2`.
+const audioStream = await voice.speak('Hello!', {
+  deliveryMode: 'BALANCED', // 'STABLE' | 'BALANCED' | 'CREATIVE'
+  language: 'en-US', // BCP-47 per-call override
+})
+```
+
+Visit the [Inworld Voice Reference](https://mastra.ai/reference/voice/inworld) for more information on the Inworld voice provider.
+
 **Speechify**:
 
 ```typescript
@@ -760,12 +971,15 @@ Visit the [Speechify Voice Reference](https://mastra.ai/reference/voice/speechif
 // Sarvam Voice Configuration
 const voice = new SarvamVoice({
   speechModel: {
-    name: 'sarvam-voice', // Example model name
+    model: 'bulbul:v3', // TTS model (bulbul:v2 or bulbul:v3)
     apiKey: process.env.SARVAM_API_KEY,
-    language: 'en-IN', // Language code
-    style: 'conversational', // Style setting
+    language: 'en-IN', // BCP-47 language code
   },
-  // Sarvam may not have a separate listening model
+  listeningModel: {
+    model: 'saarika:v2.5', // STT model (saarika:v2.5 or saaras:v3)
+    apiKey: process.env.SARVAM_API_KEY,
+  },
+  speaker: 'shubh', // Default bulbul:v3 speaker
 })
 ```
 
@@ -809,6 +1023,38 @@ const voice = new OpenAIRealtimeVoice({
 
 For more information on the OpenAI Realtime voice provider, refer to the [OpenAI Realtime Voice Reference](https://mastra.ai/reference/voice/openai-realtime).
 
+**xAI Realtime**:
+
+```typescript
+// xAI Realtime Voice Configuration
+const voice = new XAIRealtimeVoice({
+  apiKey: process.env.XAI_API_KEY,
+  model: 'grok-voice-think-fast-1.0',
+  speaker: 'eve',
+  instructions: 'You are a concise voice assistant.',
+  turnDetection: {
+    type: 'server_vad',
+    threshold: 0.85,
+    silence_duration_ms: 1000,
+    prefix_padding_ms: 333,
+  },
+  audio: {
+    input: { format: { type: 'audio/pcm', rate: 24000 } },
+    output: { format: { type: 'audio/pcm', rate: 24000 } },
+  },
+  serverTools: [
+    { type: 'web_search' },
+    {
+      type: 'mcp',
+      server_url: 'https://mcp.example.com/mcp',
+      server_label: 'business-tools',
+    },
+  ],
+})
+```
+
+Visit the [xAI Realtime Voice Reference](https://mastra.ai/reference/voice/xai-realtime) for more information on the xAI realtime voice provider.
+
 **Google Gemini Live**:
 
 ```typescript
@@ -825,6 +1071,48 @@ const voice = new GeminiLiveVoice({
 
 Visit the [Google Gemini Live Reference](https://mastra.ai/reference/voice/google-gemini-live) for more information on the Google Gemini Live voice provider.
 
+**AWS Nova Sonic**:
+
+```typescript
+// AWS Nova Sonic Voice Configuration
+const voice = new NovaSonicVoice({
+  region: 'us-east-1',
+  speaker: 'matthew',
+  sessionConfig: {
+    inferenceConfiguration: {
+      temperature: 0.7,
+      maxTokens: 1024,
+    },
+    turnDetectionConfiguration: {
+      endpointingSensitivity: 'MEDIUM',
+    },
+  },
+  // AWS Nova Sonic is a realtime bidirectional API without separate speech and listening models
+})
+```
+
+Visit the [AWS Nova Sonic Reference](https://mastra.ai/reference/voice/aws-nova-sonic) for more information on the AWS Nova Sonic voice provider.
+
+**Inworld Realtime**:
+
+```typescript
+// Inworld Realtime Voice Configuration
+const voice = new InworldRealtimeVoice({
+  apiKey: process.env.INWORLD_API_KEY,
+  model: 'inworld/models/gemma-4-26b-a4b-it',
+  speaker: 'Sarah',
+  // Typed Inworld realtime knobs (semantic VAD, playback speed, MCP tool routing, ...)
+  session: {
+    audio: {
+      output: { speed: 1.1 },
+      input: { turn_detection: { type: 'semantic_vad', eagerness: 'high' } },
+    },
+  },
+})
+```
+
+Visit the [Inworld Realtime Reference](https://mastra.ai/reference/voice/inworld-realtime) for more information on the Inworld Realtime voice provider.
+
 **AI SDK**:
 
 ```typescript
@@ -844,7 +1132,7 @@ const voiceAgent = new Agent({
   id: 'aisdk-voice-agent',
   name: 'AI SDK Voice Agent',
   instructions: 'You are a helpful assistant with voice capabilities.',
-  model: 'openai/gpt-5.4',
+  model: 'openai/gpt-5.5',
   voice,
 })
 ```
@@ -951,9 +1239,12 @@ For more information on the CompositeVoice, refer to the [CompositeVoice Referen
 - [MastraVoice](https://mastra.ai/reference/voice/mastra-voice)
 - [OpenAI Voice](https://mastra.ai/reference/voice/openai)
 - [OpenAI Realtime Voice](https://mastra.ai/reference/voice/openai-realtime)
+- [xAI Realtime Voice](https://mastra.ai/reference/voice/xai-realtime)
 - [Azure Voice](https://mastra.ai/reference/voice/azure)
 - [Google Voice](https://mastra.ai/reference/voice/google)
 - [Google Gemini Live Voice](https://mastra.ai/reference/voice/google-gemini-live)
+- [AWS Nova Sonic Voice](https://mastra.ai/reference/voice/aws-nova-sonic)
 - [Deepgram Voice](https://mastra.ai/reference/voice/deepgram)
+- [Inworld Voice](https://mastra.ai/reference/voice/inworld)
 - [PlayAI Voice](https://mastra.ai/reference/voice/playai)
 - [Voice Examples](https://github.com/mastra-ai/voice-examples)