@mastra/mcp-docs-server 1.0.0-beta.2 → 1.0.0-beta.4

package/.docs/raw/reference/vectors/pinecone.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Pinecone Vector Store | Vectors | Mastra Docs"
+title: "Reference: Pinecone Vector Store | Vectors"
 description: Documentation for the PineconeVector class in Mastra, which provides an interface to Pinecone's vector database.
 ---
 
@@ -12,6 +12,11 @@ It provides real-time vector search, with features like hybrid search, metadata
 
 <PropertiesTable
   content={[
+    {
+      name: "id",
+      type: "string",
+      description: "Unique identifier for this vector store instance",
+    },
     {
       name: "apiKey",
       type: "string",
@@ -20,7 +25,22 @@ It provides real-time vector search, with features like hybrid search, metadata
     {
       name: "environment",
       type: "string",
-      description: 'Pinecone environment (e.g., "us-west1-gcp")',
+      isOptional: true,
+      description: "Pinecone environment controller host URL",
+    },
+    {
+      name: "cloud",
+      type: "'aws' | 'gcp' | 'azure'",
+      isOptional: true,
+      defaultValue: "aws",
+      description: "Cloud provider for Pinecone serverless",
+    },
+    {
+      name: "region",
+      type: "string",
+      isOptional: true,
+      defaultValue: "us-east-1",
+      description: "Region for Pinecone serverless",
     },
   ]}
 />

package/.docs/raw/reference/vectors/qdrant.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Qdrant Vector Store | Vectors | Mastra Docs"
+title: "Reference: Qdrant Vector Store | Vectors"
 description: Documentation for integrating Qdrant with Mastra, a vector similarity search engine for managing vectors and payloads.
 ---
 

package/.docs/raw/reference/vectors/s3vectors.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Amazon S3 Vectors Store | Vectors | Mastra Docs"
+title: "Reference: Amazon S3 Vectors Store | Vectors"
 description: Documentation for the S3Vectors class in Mastra, which provides vector search using Amazon S3 Vectors (Preview).
 ---
 

package/.docs/raw/reference/vectors/turbopuffer.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Turbopuffer Vector Store | Vectors | Mastra Docs"
+title: "Reference: Turbopuffer Vector Store | Vectors"
 description: Documentation for integrating Turbopuffer with Mastra, a high-performance vector database for efficient similarity search.
 ---
 

package/.docs/raw/reference/vectors/upstash.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Upstash Vector Store | Vectors | Mastra Docs"
+title: "Reference: Upstash Vector Store | Vectors"
 description: Documentation for the UpstashVector class in Mastra, which provides vector search using Upstash Vector.
 ---
 

package/.docs/raw/reference/vectors/vectorize.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Cloudflare Vector Store | Vectors | Mastra Docs"
+title: "Reference: Cloudflare Vector Store | Vectors"
 description: Documentation for the CloudflareVector class in Mastra, which provides vector search using Cloudflare Vectorize.
 ---
 

package/.docs/raw/reference/voice/azure.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Azure | Voice | Mastra Docs"
+title: "Reference: Azure | Voice"
 description: "Documentation for the AzureVoice class, providing text-to-speech and speech-to-text capabilities using Azure Cognitive Services."
 ---
 
@@ -8,6 +8,8 @@ description: "Documentation for the AzureVoice class, providing text-to-speech a
 The AzureVoice class in Mastra provides text-to-speech and speech-to-text capabilities using Microsoft Azure Cognitive Services.
 
 ## Usage Example
+This requires Azure Speech Services credentials that can be provided through environment variables or directly in the configuration:
+
 
 ```typescript
 import { AzureVoice } from "@mastra/voice-azure";
@@ -15,29 +17,25 @@ import { AzureVoice } from "@mastra/voice-azure";
 // Initialize with configuration
 const voice = new AzureVoice({
   speechModel: {
-    name: "neural",
-    apiKey: "your-azure-speech-api-key",
-    region: "eastus",
+    apiKey: "your-azure-speech-api-key", // Or use AZURE_API_KEY env var
+    region: "eastus", // Or use AZURE_REGION env var
+    voiceName: "en-US-AriaNeural", // Optional: specific voice for TTS
   },
   listeningModel: {
-    name: "whisper",
-    apiKey: "your-azure-speech-api-key",
-    region: "eastus",
+    apiKey: "your-azure-speech-api-key", // Or use AZURE_API_KEY env var
+    region: "eastus", // Or use AZURE_REGION env var
+    language: "en-US", // Optional: recognition language for STT
   },
-  speaker: "en-US-JennyNeural", // Default voice
+  speaker: "en-US-JennyNeural", // Optional: default voice
 });
 
 // Convert text to speech
 const audioStream = await voice.speak("Hello, how can I help you?", {
-  speaker: "en-US-GuyNeural", // Override default voice
-  style: "cheerful", // Voice style
+  speaker: "en-US-GuyNeural", // Optional: override default voice
 });
 
 // Convert speech to text
-const text = await voice.listen(audioStream, {
-  filetype: "wav",
-  language: "en-US",
-});
+const text = await voice.listen(audioStream);
 ```
 
 ## Configuration
@@ -69,26 +67,36 @@ const text = await voice.listen(audioStream, {
 
 ### AzureSpeechConfig
 
+Configuration object for speech synthesis (`speechModel`) and recognition (`listeningModel`).
+
 <PropertiesTable
   content={[
     {
-      name: "name",
-      type: "'neural' | 'standard' | 'whisper'",
-      description: "Model type to use. 'neural' for TTS, 'whisper' for STT.",
+      name: "apiKey",
+      type: "string",
+      description:
+        "Azure Speech Services API key (NOT Azure OpenAI key). Falls back to AZURE_API_KEY environment variable.",
       isOptional: true,
     },
     {
-      name: "apiKey",
+      name: "region",
       type: "string",
       description:
-        "Azure Speech Services API key. Falls back to AZURE_SPEECH_KEY environment variable.",
+        "Azure region (e.g., 'eastus', 'westeurope'). Falls back to AZURE_REGION environment variable.",
       isOptional: true,
     },
     {
-      name: "region",
+      name: "voiceName",
+      type: "string",
+      description:
+        "Voice ID for speech synthesis (e.g., 'en-US-AriaNeural', 'en-US-JennyNeural'). Only used in speechModel. See voice list below.",
+      isOptional: true,
+    },
+    {
+      name: "language",
       type: "string",
       description:
-        "Azure region (e.g., 'eastus', 'westeurope'). Falls back to AZURE_SPEECH_REGION environment variable.",
+        "Recognition language code (e.g., 'en-US', 'fr-FR'). Only used in listeningModel.",
       isOptional: true,
     },
   ]}
@@ -111,32 +119,14 @@ Converts text to speech using Azure's neural text-to-speech service.
     {
       name: "options.speaker",
       type: "string",
-      description: "Voice ID to use for speech synthesis.",
+      description: "Voice ID to use for speech synthesis (e.g., 'en-US-JennyNeural'). Overrides the default voice.",
       isOptional: true,
       defaultValue: "Constructor's speaker value",
     },
-    {
-      name: "options.style",
-      type: "string",
-      description: "Speaking style (e.g., 'cheerful', 'sad', 'angry').",
-      isOptional: true,
-    },
-    {
-      name: "options.rate",
-      type: "string",
-      description: "Speaking rate (e.g., 'slow', 'medium', 'fast').",
-      isOptional: true,
-    },
-    {
-      name: "options.pitch",
-      type: "string",
-      description: "Voice pitch (e.g., 'low', 'medium', 'high').",
-      isOptional: true,
-    },
   ]}
 />
 
-Returns: `Promise<NodeJS.ReadableStream>`
+Returns: `Promise<NodeJS.ReadableStream>` - Audio stream in WAV format
 
 ### listen()
 
@@ -147,31 +137,19 @@ Transcribes audio using Azure's speech-to-text service.
     {
       name: "audioStream",
       type: "NodeJS.ReadableStream",
-      description: "Audio stream to transcribe.",
+      description: "Audio stream to transcribe. Must be in WAV format.",
       isOptional: false,
     },
-    {
-      name: "options.filetype",
-      type: "string",
-      description: "Audio format of the input stream.",
-      isOptional: true,
-      defaultValue: "'wav'",
-    },
-    {
-      name: "options.language",
-      type: "string",
-      description: "Language code for transcription.",
-      isOptional: true,
-      defaultValue: "'en-US'",
-    },
   ]}
 />
 
-Returns: `Promise<string>`
+Returns: `Promise<string>` - The recognized text from the audio
+
+**Note:** Language and recognition settings are configured in the `listeningModel` configuration during initialization, not passed as options to this method.
 
 ### getSpeakers()
 
-Returns an array of available voice options, where each node contains:
+Returns an array of available voice options (200+ voices), where each node contains:
 
 <PropertiesTable
   content={[
@@ -179,40 +157,77 @@ Returns an array of available voice options, where each node contains:
       name: "voiceId",
       type: "string",
       description:
-        "Unique identifier for the voice (e.g., 'en-US-JennyNeural')",
-      isOptional: false,
-    },
-    {
-      name: "name",
-      type: "string",
-      description: "Human-readable name of the voice",
+        "Unique identifier for the voice (e.g., 'en-US-JennyNeural', 'fr-FR-DeniseNeural')",
       isOptional: false,
     },
     {
-      name: "locale",
+      name: "language",
       type: "string",
-      description: "Language locale of the voice (e.g., 'en-US')",
+      description: "Language code extracted from voice ID (e.g., 'en', 'fr')",
       isOptional: false,
     },
     {
-      name: "gender",
+      name: "region",
       type: "string",
-      description: "Gender of the voice ('Male' or 'Female')",
+      description: "Region code extracted from voice ID (e.g., 'US', 'GB', 'FR')",
       isOptional: false,
     },
-    {
-      name: "styles",
-      type: "string[]",
-      description: "Available speaking styles for the voice",
-      isOptional: true,
-    },
   ]}
 />
 
-## Notes
+Returns: `Promise<Array<{ voiceId: string; language: string; region: string; }>>`
+
+## Important Notes
+
+### Azure Speech Services vs Azure OpenAI
+
+**⚠️ Critical:** This package uses **Azure Speech Services**, which is different from **Azure OpenAI Services**.
+
+- **DO NOT** use your `AZURE_OPENAI_API_KEY` for this package
+- **DO** use an Azure Speech Services subscription key (obtain from Azure Portal under "Speech Services")
+- These are separate Azure resources with different API keys and endpoints
+
+### Environment Variables
+
+API keys and regions can be provided via constructor options or environment variables:
+
+- `AZURE_API_KEY` - Your Azure Speech Services subscription key
+- `AZURE_REGION` - Your Azure region (e.g., 'eastus', 'westeurope')
+
+### Voice Capabilities
+
+- Azure offers 200+ neural voices across 50+ languages
+- Each voice ID follows the format: `{language}-{region}-{name}Neural` (e.g., 'en-US-JennyNeural')
+- Some voices include multilingual support or HD quality variants
+- Audio output is in WAV format
+- Audio input for recognition must be in WAV format
+
+## Available Voices
+
+Azure provides 200+ neural voices across many languages. Some popular English voices include:
+
+- **US English:**
+  - `en-US-AriaNeural` (Female, default)
+  - `en-US-JennyNeural` (Female)
+  - `en-US-GuyNeural` (Male)
+  - `en-US-DavisNeural` (Male)
+  - `en-US-AvaNeural` (Female)
+  - `en-US-AndrewNeural` (Male)
+
+- **British English:**
+  - `en-GB-SoniaNeural` (Female)
+  - `en-GB-RyanNeural` (Male)
+  - `en-GB-LibbyNeural` (Female)
+
+- **Australian English:**
+  - `en-AU-NatashaNeural` (Female)
+  - `en-AU-WilliamNeural` (Male)
+
+To get a complete list of all 200+ voices:
+
+```typescript
+const voices = await voice.getSpeakers();
+console.log(voices); // Array of { voiceId, language, region }
+```
 
-- API keys can be provided via constructor options or environment variables (AZURE_SPEECH_KEY and AZURE_SPEECH_REGION)
-- Azure offers a wide range of neural voices across many languages
-- Some voices support speaking styles like cheerful, sad, angry, etc.
-- Speech recognition supports multiple audio formats and languages
-- Azure's speech services provide high-quality neural voices with natural-sounding speech
+For more information, see the [Azure Neural TTS documentation](https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support?tabs=tts).

package/.docs/raw/reference/voice/cloudflare.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Cloudflare | Voice | Mastra Docs"
+title: "Reference: Cloudflare | Voice"
 description: "Documentation for the CloudflareVoice class, providing text-to-speech capabilities using Cloudflare Workers AI."
 ---
 

package/.docs/raw/reference/voice/composite-voice.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: CompositeVoice | Voice | Mastra Docs"
+title: "Reference: CompositeVoice | Voice"
 description: "Documentation for the CompositeVoice class, which enables combining multiple voice providers for flexible text-to-speech and speech-to-text operations."
 ---
 
@@ -7,31 +7,7 @@ description: "Documentation for the CompositeVoice class, which enables combinin
 
 The CompositeVoice class allows you to combine different voice providers for text-to-speech and speech-to-text operations. This is particularly useful when you want to use the best provider for each operation - for example, using OpenAI for speech-to-text and PlayAI for text-to-speech.
 
-CompositeVoice is used internally by the Agent class to provide flexible voice capabilities.
-
-## Usage Example
-
-```typescript
-import { CompositeVoice } from "@mastra/core/voice";
-import { OpenAIVoice } from "@mastra/voice-openai";
-import { PlayAIVoice } from "@mastra/voice-playai";
-
-// Create voice providers
-const openai = new OpenAIVoice();
-const playai = new PlayAIVoice();
-
-// Use OpenAI for listening (speech-to-text) and PlayAI for speaking (text-to-speech)
-const voice = new CompositeVoice({
-  input: openai,
-  output: playai,
-});
-
-// Convert speech to text using OpenAI
-const text = await voice.listen(audioStream);
-
-// Convert text to speech using PlayAI
-const audio = await voice.speak("Hello, world!");
-```
+CompositeVoice supports both Mastra voice providers and AI SDK model providers
 
 ## Constructor Parameters
 
@@ -45,14 +21,20 @@ const audio = await voice.speak("Hello, world!");
     },
     {
       name: "config.input",
-      type: "MastraVoice",
-      description: "Voice provider to use for speech-to-text operations",
+      type: "MastraVoice | TranscriptionModel",
+      description: "Voice provider or AI SDK transcription model to use for speech-to-text operations. AI SDK models are automatically wrapped.",
       isOptional: true,
     },
     {
       name: "config.output",
+      type: "MastraVoice | SpeechModel",
+      description: "Voice provider or AI SDK speech model to use for text-to-speech operations. AI SDK models are automatically wrapped.",
+      isOptional: true,
+    },
+    {
+      name: "config.realtime",
       type: "MastraVoice",
-      description: "Voice provider to use for text-to-speech operations",
+      description: "Voice provider to use for real-time speech-to-speech operations",
       isOptional: true,
     },
   ]}
@@ -142,3 +124,64 @@ Notes:
 - If no speaking provider is configured, returns an empty array
 - Each voice object will have at least a voiceId property
 - Additional voice properties depend on the speaking provider
+
+## Usage Examples
+
+### Using Mastra Voice Providers
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { OpenAIVoice } from "@mastra/voice-openai";
+import { PlayAIVoice } from "@mastra/voice-playai";
+
+// Create voice providers
+const openai = new OpenAIVoice();
+const playai = new PlayAIVoice();
+
+// Use OpenAI for listening (speech-to-text) and PlayAI for speaking (text-to-speech)
+const voice = new CompositeVoice({
+  input: openai,
+  output: playai,
+});
+
+// Convert speech to text using OpenAI
+const text = await voice.listen(audioStream);
+
+// Convert text to speech using PlayAI
+const audio = await voice.speak("Hello, world!");
+```
+
+### Using AI SDK Model Providers
+
+You can pass AI SDK transcription and speech models directly to CompositeVoice:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { openai } from "@ai-sdk/openai";
+import { elevenlabs } from "@ai-sdk/elevenlabs";
+
+// Use AI SDK models directly - they will be auto-wrapped
+const voice = new CompositeVoice({
+  input: openai.transcription('whisper-1'),      // AI SDK transcription
+  output: elevenlabs.speech('eleven_turbo_v2'),  // AI SDK speech
+});
+
+// Works the same way as with Mastra providers
+const text = await voice.listen(audioStream);
+const audio = await voice.speak("Hello from AI SDK!");
+```
+
+### Mix and Match
+
+You can combine Mastra providers with AI SDK models:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { PlayAIVoice } from "@mastra/voice-playai";
+import { groq } from "@ai-sdk/groq";
+
+const voice = new CompositeVoice({
+  input: groq.transcription('whisper-large-v3'),  // AI SDK for STT
+  output: new PlayAIVoice(),                       // Mastra for TTS
+});
+```

package/.docs/raw/reference/voice/deepgram.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Deepgram | Voice | Mastra Docs"
+title: "Reference: Deepgram | Voice"
 description: "Documentation for the Deepgram voice implementation, providing text-to-speech and speech-to-text capabilities with multiple voice models and languages."
 ---
 

package/.docs/raw/reference/voice/elevenlabs.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: ElevenLabs | Voice | Mastra Docs"
+title: "Reference: ElevenLabs | Voice"
 description: "Documentation for the ElevenLabs voice implementation, offering high-quality text-to-speech capabilities with multiple voice models and natural-sounding synthesis."
 ---
 

package/.docs/raw/reference/voice/google-gemini-live.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Google Gemini Live Voice | Voice | Mastra Docs"
+title: "Reference: Google Gemini Live Voice | Voice"
 description: "Documentation for the GeminiLiveVoice class, providing real-time multimodal voice interactions using Google's Gemini Live API with support for both Gemini API and Vertex AI."
 ---
 

package/.docs/raw/reference/voice/google.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Google | Voice | Mastra Docs"
+title: "Reference: Google | Voice"
 description: "Documentation for the Google Voice implementation, providing text-to-speech and speech-to-text capabilities."
 ---
 

package/.docs/raw/reference/voice/mastra-voice.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: MastraVoice | Voice | Mastra Docs"
+title: "Reference: MastraVoice | Voice"
 description: "Documentation for the MastraVoice abstract base class, which defines the core interface for all voice services in Mastra, including speech-to-speech capabilities."
 ---
 

package/.docs/raw/reference/voice/murf.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Murf | Voice | Mastra Docs"
+title: "Reference: Murf | Voice"
 description: "Documentation for the Murf voice implementation, providing text-to-speech capabilities."
 ---
 

package/.docs/raw/reference/voice/openai-realtime.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: OpenAI Realtime Voice | Voice | Mastra Docs"
+title: "Reference: OpenAI Realtime Voice | Voice"
 description: "Documentation for the OpenAIRealtimeVoice class, providing real-time text-to-speech and speech-to-text capabilities via WebSockets."
 ---
 

package/.docs/raw/reference/voice/openai.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: OpenAI | Voice | Mastra Docs"
+title: "Reference: OpenAI | Voice"
 description: "Documentation for the OpenAIVoice class, providing text-to-speech and speech-to-text capabilities."
 ---
 

package/.docs/raw/reference/voice/playai.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: PlayAI | Voice | Mastra Docs"
+title: "Reference: PlayAI | Voice"
 description: "Documentation for the PlayAI voice implementation, providing text-to-speech capabilities."
 ---
 

package/.docs/raw/reference/voice/sarvam.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Sarvam | Voice | Mastra Docs"
+title: "Reference: Sarvam | Voice"
 description: "Documentation for the Sarvam class, providing text-to-speech and speech-to-text capabilities."
 ---
 

package/.docs/raw/reference/voice/speechify.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Speechify | Voice | Mastra Docs"
+title: "Reference: Speechify | Voice"
 description: "Documentation for the Speechify voice implementation, providing text-to-speech capabilities."
 ---
 

package/.docs/raw/reference/voice/voice.addInstructions.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: voice.addInstructions() | Voice | Mastra Docs"
+title: "Reference: voice.addInstructions() | Voice"
 description: "Documentation for the addInstructions() method available in voice providers, which adds instructions to guide the voice model's behavior."
 ---
 

package/.docs/raw/reference/voice/voice.addTools.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: voice.addTools() | Voice | Mastra Docs"
+title: "Reference: voice.addTools() | Voice"
 description: "Documentation for the addTools() method available in voice providers, which equips voice models with function calling capabilities."
 ---
 

package/.docs/raw/reference/voice/voice.answer.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: voice.answer() | Voice | Mastra Docs"
+title: "Reference: voice.answer() | Voice"
 description: "Documentation for the answer() method available in real-time voice providers, which triggers the voice provider to generate a response."
 ---
 

package/.docs/raw/reference/voice/voice.close.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: voice.close() | Voice | Mastra Docs"
+title: "Reference: voice.close() | Voice"
 description: "Documentation for the close() method available in voice providers, which disconnects from real-time voice services."
 ---
 

package/.docs/raw/reference/voice/voice.connect.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: voice.connect() | Voice | Mastra Docs"
+title: "Reference: voice.connect() | Voice"
 description: "Documentation for the connect() method available in real-time voice providers, which establishes a connection for speech-to-speech communication."
 ---
 

package/.docs/raw/reference/voice/voice.events.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Voice Events | Voice | Mastra Docs"
+title: "Reference: Voice Events | Voice"
 description: "Documentation for events emitted by voice providers, particularly for real-time voice interactions."
 ---
 

package/.docs/raw/reference/voice/voice.getSpeakers.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: voice.getSpeakers() | Voice Providers | Mastra Docs"
+title: "Reference: voice.getSpeakers() | Voice Providers"
 description: "Documentation for the getSpeakers() method available in voice providers, which retrieves available voice options."
 ---