@mastra/mcp-docs-server 1.1.8 → 1.1.9-alpha.1

package/.docs/reference/voice/murf.md

@@ -2,7 +2,7 @@
 
 The Murf voice implementation in Mastra provides text-to-speech (TTS) capabilities using Murf's AI voice service. It supports multiple voices across different languages.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { MurfVoice } from '@mastra/voice-murf'
@@ -43,7 +43,7 @@ const audioStream = await voice.speak('Hello, world!', {
 const voices = await voice.getSpeakers()
 ```
 
-## Constructor Parameters
+## Constructor parameters
 
 **speechModel** (`MurfConfig`): Configuration for text-to-speech functionality (Default: `{ name: 'GEN2' }`)
 
@@ -79,7 +79,7 @@ const voices = await voice.getSpeakers()
 
 ## Methods
 
-### speak()
+### `speak()`
 
 Converts text to speech using Murf's API.
 
@@ -93,7 +93,7 @@ Converts text to speech using Murf's API.
 
 Returns: `Promise<NodeJS.ReadableStream>`
 
-### getSpeakers()
+### `getSpeakers()`
 
 Returns an array of available voice options, where each node contains:
 
@@ -105,14 +105,14 @@ Returns an array of available voice options, where each node contains:
 
 **gender** (`string`): Gender of the voice
 
-### listen()
+### `listen()`
 
-This method is not supported by Murf and will throw an error. Murf does not provide speech-to-text functionality.
+This method isn't supported by Murf and will throw an error. Murf doesn't provide speech-to-text functionality.
 
-## Important Notes
+## Important notes
 
 1. A Murf API key is required. Set it via the `MURF_API_KEY` environment variable or pass it in the constructor.
 2. The service uses GEN2 as the default model version.
 3. Speech properties can be set at the constructor level and overridden per request.
 4. The service supports extensive audio customization through properties like format, sample rate, and channel type.
-5. Speech-to-text functionality is not supported.
+5. Speech-to-text functionality isn't supported.

package/.docs/reference/voice/openai-realtime.md

@@ -1,8 +1,8 @@
-# OpenAI Realtime Voice
+# OpenAI Realtime voice
 
 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
+## Usage example
 
 ```typescript
 import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
@@ -55,7 +55,7 @@ voice.connect()
 
 ## Configuration
 
-### Constructor Options
+### Constructor options
 
 **model** (`string`): The model ID to use for real-time voice interactions. (Default: `'gpt-5.1-realtime-preview-2024-12-17'`)
 
@@ -75,23 +75,25 @@ voice.connect()
 
 ## Methods
 
-### connect()
+### `connect()`
 
-Establishes a connection to the OpenAI realtime service. Must be called before using speak, listen, or send functions.
+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()
+### `speak()`
 
 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.speaker** (`string`): Voice ID to use for this specific speech request. (Default: `Constructor's speaker value`)
+**options** (`Options`): Configuration options.
+
+**options.speaker** (`string`): Voice ID to use for this specific speech request.
 
 Returns: `Promise<void>`
 
-### listen()
+### `listen()`
 
 Processes audio input for speech recognition. Takes a readable stream of audio data and emits a 'listening' event with the transcribed text.
 
@@ -99,7 +101,7 @@ Processes audio input for speech recognition. Takes a readable stream of audio d
 
 Returns: `Promise<void>`
 
-### send()
+### `send()`
 
 Streams audio data in real-time to the OpenAI service for continuous audio streaming scenarios like live microphone input.
 
@@ -107,7 +109,7 @@ Streams audio data in real-time to the OpenAI service for continuous audio strea
 
 Returns: `Promise<void>`
 
-### updateConfig()
+### `updateConfig()`
 
 Updates the session configuration for the voice instance. This can be used to modify voice settings, turn detection, and other parameters.
 
@@ -115,7 +117,7 @@ Updates the session configuration for the voice instance. This can be used to mo
 
 Returns: `void`
 
-### addTools()
+### `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.
 
@@ -123,19 +125,19 @@ Adds a set of tools to the voice instance. Tools allow the model to perform addi
 
 Returns: `void`
 
-### close()
+### `close()`
 
-Disconnects from the OpenAI realtime session and cleans up resources. Should be called when you're done with the voice instance.
+Disconnects from the OpenAI Realtime session and cleans up resources. Should be called when you're done with the voice instance.
 
 Returns: `void`
 
-### getSpeakers()
+### `getSpeakers()`
 
 Returns a list of available voice speakers.
 
 Returns: `Promise<Array<{ voiceId: string; [key: string]: any }>>`
 
-### on()
+### `on()`
 
 Registers an event listener for voice events.
 
@@ -145,7 +147,7 @@ Registers an event listener for voice events.
 
 Returns: `void`
 
-### off()
+### `off()`
 
 Removes a previously registered event listener.
 
@@ -179,7 +181,7 @@ You can also listen to [OpenAI Realtime utility events](https://github.com/opena
 
 **openAIRealtime:conversation.item.completed** (`event`): Emitted when an item in the conversation is completed.
 
-## Available Voices
+## Available voices
 
 The following voice options are available:
 

package/.docs/reference/voice/openai.md

@@ -2,7 +2,7 @@
 
 The OpenAIVoice class in Mastra provides text-to-speech and speech-to-text capabilities using OpenAI's models.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIVoice } from '@mastra/voice-openai'
@@ -37,7 +37,7 @@ const text = await voice.listen(audioStream, {
 
 ## Configuration
 
-### Constructor Options
+### Constructor options
 
 **speechModel** (`OpenAIConfig`): Configuration for text-to-speech synthesis. (Default: `{ name: 'tts-1' }`)
 
@@ -55,29 +55,33 @@ const text = await voice.listen(audioStream, {
 
 ## Methods
 
-### speak()
+### `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.speaker** (`OpenAIVoiceId`): Voice ID to use for speech synthesis. (Default: `Constructor's speaker value`)
+**options** (`Options`): Configuration options.
 
-**options.speed** (`number`): Speech speed multiplier. (Default: `1.0`)
+**options.speaker** (`OpenAIVoiceId`): Voice ID to use for speech synthesis.
+
+**options.speed** (`number`): Speech speed multiplier.
 
 Returns: `Promise<NodeJS.ReadableStream>`
 
-### listen()
+### `listen()`
 
 Transcribes audio using OpenAI's Whisper model.
 
 **audioStream** (`NodeJS.ReadableStream`): Audio stream to transcribe.
 
-**options.filetype** (`string`): Audio format of the input stream. (Default: `'mp3'`)
+**options** (`Options`): Configuration options.
+
+**options.filetype** (`string`): Audio format of the input stream.
 
 Returns: `Promise<string>`
 
-### getSpeakers()
+### `getSpeakers()`
 
 Returns an array of available voice options, where each node contains:
 

package/.docs/reference/voice/playai.md

@@ -2,7 +2,7 @@
 
 The PlayAI voice implementation in Mastra provides text-to-speech capabilities using PlayAI's API.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { PlayAIVoice } from '@mastra/voice-playai'
@@ -27,7 +27,7 @@ const audioStream = await voice.speak('Hello, world!', {
 })
 ```
 
-## Constructor Parameters
+## Constructor parameters
 
 **speechModel** (`PlayAIConfig`): Configuration for text-to-speech functionality (Default: `{ name: 'PlayDialog' }`)
 
@@ -41,17 +41,19 @@ const audioStream = await voice.speak('Hello, world!', {
 
 ## Methods
 
-### speak()
+### `speak()`
 
 Converts text to speech using the configured speech model and voice.
 
 **input** (`string | NodeJS.ReadableStream`): Text to convert to speech. If a stream is provided, it will be converted to text first.
 
-**options.speaker** (`string`): Override the default speaker for this request (Default: `Constructor's speaker value`)
+**options** (`Options`): Configuration options.
+
+**options.speaker** (`string`): Override the default speaker for this request
 
 Returns: `Promise<NodeJS.ReadableStream>`.
 
-### getSpeakers()
+### `getSpeakers()`
 
 Returns an array of available voice options, where each node contains:
 
@@ -67,9 +69,9 @@ Returns an array of available voice options, where each node contains:
 
 **voiceId** (`string`): Unique identifier for the voice
 
-### listen()
+### `listen()`
 
-This method is not supported by PlayAI and will throw an error. PlayAI does not provide speech-to-text functionality.
+This method isn't supported by PlayAI and will throw an error. PlayAI doesn't provide speech-to-text functionality.
 
 ## Notes
 

package/.docs/reference/voice/sarvam.md

@@ -2,7 +2,7 @@
 
 The SarvamVoice class in Mastra provides text-to-speech and speech-to-text capabilities using Sarvam AI models.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { SarvamVoice } from '@mastra/voice-sarvam'
@@ -49,7 +49,7 @@ const text = await voice.listen(audioStream, {
 
 ## Configuration
 
-### Constructor Options
+### Constructor options
 
 **speechModel** (`SarvamVoiceConfig`): Configuration for text-to-speech synthesis. (Default: `{ model: 'bulbul:v1', language: 'en-IN' }`)
 
@@ -87,17 +87,19 @@ const text = await voice.listen(audioStream, {
 
 ## Methods
 
-### speak()
+### `speak()`
 
 Converts text to speech using Sarvam's text-to-speech models.
 
 **input** (`string | NodeJS.ReadableStream`): Text or text stream to convert to speech.
 
-**options.speaker** (`SarvamVoiceId`): Voice ID to use for speech synthesis. (Default: `Constructor's speaker value`)
+**options** (`Options`): Configuration options.
+
+**options.speaker** (`SarvamVoiceId`): Voice ID to use for speech synthesis.
 
 Returns: `Promise<NodeJS.ReadableStream>`
 
-### listen()
+### `listen()`
 
 Transcribes audio using Sarvam's speech recognition models.
 
@@ -107,7 +109,7 @@ Transcribes audio using Sarvam's speech recognition models.
 
 Returns: `Promise<string>`
 
-### getSpeakers()
+### `getSpeakers()`
 
 Returns an array of available voice options.
 

package/.docs/reference/voice/speechify.md

@@ -2,7 +2,7 @@
 
 The Speechify voice implementation in Mastra provides text-to-speech capabilities using Speechify's API.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { SpeechifyVoice } from '@mastra/voice-speechify'
@@ -25,7 +25,7 @@ const audioStream = await voice.speak('Hello, world!', {
 })
 ```
 
-## Constructor Parameters
+## Constructor parameters
 
 **speechModel** (`SpeechifyConfig`): Configuration for text-to-speech functionality (Default: `{ name: 'simba-english' }`)
 
@@ -37,19 +37,21 @@ const audioStream = await voice.speak('Hello, world!', {
 
 ## Methods
 
-### speak()
+### `speak()`
 
 Converts text to speech using the configured speech model and voice.
 
 **input** (`string | NodeJS.ReadableStream`): Text to convert to speech. If a stream is provided, it will be converted to text first.
 
-**options.speaker** (`string`): Override the default speaker for this request (Default: `Constructor's speaker value`)
+**options** (`Options`): Configuration options.
 
-**options.model** (`VoiceModelName`): Override the default model for this request (Default: `Constructor's model value`)
+**options.speaker** (`string`): Override the default speaker for this request
+
+**options.model** (`VoiceModelName`): Override the default model for this request
 
 Returns: `Promise<NodeJS.ReadableStream>`
 
-### getSpeakers()
+### `getSpeakers()`
 
 Returns an array of available voice options, where each node contains:
 
@@ -61,13 +63,13 @@ Returns an array of available voice options, where each node contains:
 
 **gender** (`string`): Gender of the voice
 
-### listen()
+### `listen()`
 
-This method is not supported by Speechify and will throw an error. Speechify does not provide speech-to-text functionality.
+This method isn't supported by Speechify and will throw an error. Speechify doesn't provide speech-to-text functionality.
 
 ## Notes
 
 - Speechify requires an API key for authentication
 - The default model is 'simba-english'
-- Speech-to-text functionality is not supported
+- Speech-to-text functionality isn't supported
 - Additional audio stream options can be passed through the speak() method's options parameter

package/.docs/reference/voice/voice.addInstructions.md

@@ -2,7 +2,7 @@
 
 The `addInstructions()` method equips a voice provider with instructions that guide the model's behavior during real-time interactions. This is particularly useful for real-time voice providers that maintain context across a conversation.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
@@ -41,13 +41,13 @@ await voice.connect()
 
 **instructions** (`string`): Instructions to guide the voice model's behavior
 
-## Return Value
+## Return value
 
-This method does not return a value.
+This method doesn't return a value.
 
 ## Notes
 
-- Instructions are most effective when they are clear, specific, and relevant to the voice interaction
+- Instructions are most effective when they're clear, specific, and relevant to the voice interaction
 - This method is primarily used with real-time voice providers that maintain conversation context
 - If called on a voice provider that doesn't support instructions, it will log a warning and do nothing
 - Instructions added with this method are typically combined with any instructions provided by an associated Agent

package/.docs/reference/voice/voice.addTools.md

@@ -2,7 +2,7 @@
 
 The `addTools()` method equips a voice provider with tools (functions) that can be called by the model during real-time interactions. This enables voice assistants to perform actions like searching for information, making calculations, or interacting with external systems.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
@@ -52,9 +52,9 @@ await voice.connect()
 
 **tools** (`ToolsInput`): Object containing tool definitions that can be called by the voice model
 
-## Return Value
+## Return value
 
-This method does not return a value.
+This method doesn't return a value.
 
 ## Notes
 

package/.docs/reference/voice/voice.answer.md

@@ -2,7 +2,7 @@
 
 The `answer()` method is used in real-time voice providers to trigger the AI to generate a response. This method is particularly useful in speech-to-speech conversations where you need to explicitly signal the AI to respond after receiving user input.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
@@ -41,7 +41,7 @@ await voice.answer()
 
 **options** (`Record<string, unknown>`): Provider-specific options for the response
 
-## Return Value
+## Return value
 
 Returns a `Promise<void>` that resolves when the response has been triggered.
 

package/.docs/reference/voice/voice.close.md

@@ -2,7 +2,7 @@
 
 The `close()` method disconnects from a real-time voice service and cleans up resources. This is important for properly ending voice sessions and preventing resource leaks.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
@@ -36,11 +36,11 @@ setTimeout(() => {
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
-## Return Value
+## Return value
 
-This method does not return a value.
+This method doesn't return a value.
 
 ## Notes
 

package/.docs/reference/voice/voice.connect.md

@@ -2,7 +2,7 @@
 
 The `connect()` method establishes a WebSocket or WebRTC connection for real-time speech-to-speech communication. This method must be called before using other real-time features like `send()` or `answer()`.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
@@ -48,21 +48,23 @@ await voice.connect({
 
 **options** (`Record<string, unknown>`): Provider-specific connection options
 
-## Return Value
+## Return value
 
 Returns a `Promise<void>` that resolves when the connection is successfully established.
 
-## Provider-Specific Options
+## Provider-specific options
 
 Each real-time voice provider may support different options for the `connect()` method:
 
 ### OpenAI Realtime
 
-**options.timeout** (`number`): Connection timeout in milliseconds (Default: `30000`)
+**options** (`Options`): Configuration options.
 
-**options.reconnect** (`boolean`): Whether to automatically reconnect on connection loss (Default: `false`)
+**options.timeout** (`number`): Connection timeout in milliseconds
 
-## Using with CompositeVoice
+**options.reconnect** (`boolean`): Whether to automatically reconnect on connection loss
+
+## Using with `CompositeVoice`
 
 When using `CompositeVoice`, the `connect()` method delegates to the configured real-time provider:
 
@@ -86,7 +88,7 @@ await voice.connect()
 - Some providers may automatically reconnect on connection loss, depending on their implementation
 - Connection errors will typically be thrown as exceptions that should be caught and handled
 
-## Related Methods
+## Related methods
 
 - [voice.send()](https://mastra.ai/reference/voice/voice.send) - Sends audio data to the voice provider
 - [voice.answer()](https://mastra.ai/reference/voice/voice.answer) - Triggers the voice provider to respond

package/.docs/reference/voice/voice.events.md

@@ -1,8 +1,8 @@
-# Voice Events
+# Voice events
 
 Voice providers emit various events during real-time voice interactions. These events can be listened to using the [voice.on()](https://mastra.ai/reference/voice/voice.on) method and are particularly important for building interactive voice applications.
 
-## Common Events
+## Common events
 
 These events are commonly implemented across real-time voice providers:
 
@@ -32,6 +32,6 @@ These events are commonly implemented across real-time voice providers:
 
 - Not all events are supported by all voice providers
 - The exact payload structure may vary between providers
-- For non-real-time providers, most of these events will not be emitted
+- For non-real-time providers, most of these events won't be emitted
 - Events are useful for building interactive UIs that respond to the conversation state
-- Consider using the [voice.off()](https://mastra.ai/reference/voice/voice.off) method to remove event listeners when they are no longer needed
+- Consider using the [voice.off()](https://mastra.ai/reference/voice/voice.off) method to remove event listeners when they're no longer needed

package/.docs/reference/voice/voice.getSpeakers.md

@@ -2,7 +2,7 @@
 
 The `getSpeakers()` method retrieves a list of available voice options (speakers) from the voice provider. This allows applications to present users with voice choices or programmatically select the most appropriate voice for different contexts.
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIVoice } from '@mastra/voice-openai'
@@ -32,13 +32,13 @@ await elevenLabsVoice.speak(text, { speaker: elevenLabsSpeakers[0].voiceId })
 
 ## Parameters
 
-This method does not accept any parameters.
+This method doesn't accept any parameters.
 
-## Return Value
+## Return value
 
 **Promise\<Array<{ voiceId: string } & TSpeakerMetadata>>** (`Promise`): A promise that resolves to an array of voice options, where each option contains at least a voiceId property and may include additional provider-specific metadata.
 
-## Provider-Specific Metadata
+## Provider-specific metadata
 
 Different voice providers return different metadata for their voices:
 

package/.docs/reference/voice/voice.listen.md

@@ -8,7 +8,7 @@ The `listen()` method is a core function available in all Mastra voice providers
 
 **options** (`object`): Provider-specific options for speech recognition
 
-## Return Value
+## Return value
 
 Returns one of the following:
 
@@ -16,13 +16,15 @@ Returns one of the following:
 - `Promise<NodeJS.ReadableStream>`: A promise that resolves to a stream of transcribed text (for streaming transcription)
 - `Promise<void>`: For real-time providers that emit 'writing' events instead of returning text directly
 
-## Provider-Specific Options
+## Provider-specific options
 
 Each voice provider may support additional options specific to their implementation. Here are some examples:
 
 ### OpenAI
 
-**options.filetype** (`string`): Audio file format (e.g., 'mp3', 'wav', 'm4a') (Default: `'mp3'`)
+**options** (`Options`): Configuration options.
+
+**options.filetype** (`string`): Audio file format (e.g., 'mp3', 'wav', 'm4a')
 
 **options.prompt** (`string`): Text to guide the model's transcription
 
@@ -30,17 +32,21 @@ Each voice provider may support additional options specific to their implementat
 
 ### Google
 
-**options.stream** (`boolean`): Whether to use streaming recognition (Default: `false`)
+**options** (`Options`): Configuration options.
+
+**options.stream** (`boolean`): Whether to use streaming recognition
 
-**options.config** (`object`): Recognition configuration from Google Cloud Speech-to-Text API (Default: `{ encoding: 'LINEAR16', languageCode: 'en-US' }`)
+**options.config** (`object`): Recognition configuration from Google Cloud Speech-to-Text API
 
 ### Deepgram
 
-**options.model** (`string`): Deepgram model to use for transcription (Default: `'nova-2'`)
+**options** (`Options`): Configuration options.
+
+**options.model** (`string`): Deepgram model to use for transcription
 
-**options.language** (`string`): Language code for transcription (Default: `'en'`)
+**options.language** (`string`): Language code for transcription
 
-## Usage Example
+## Usage example
 
 ```typescript
 import { OpenAIVoice } from '@mastra/voice-openai'
@@ -75,7 +81,7 @@ const transcriptWithOptions = await voice.listen(audioStream, {
 })
 ```
 
-## Using with CompositeVoice
+## Using with `CompositeVoice`
 
 When using `CompositeVoice`, the `listen()` method delegates to the configured listening provider:
 
@@ -124,7 +130,7 @@ const transcriptWithOptions = await voice.listen(audioStream, {
 
 See the [CompositeVoice reference](https://mastra.ai/reference/voice/composite-voice) for more details on AI SDK integration.
 
-## Realtime Voice Providers
+## Realtime voice providers
 
 When using realtime voice providers like `OpenAIRealtimeVoice`, the `listen()` method behaves differently:
 
@@ -157,7 +163,7 @@ await voice.listen(microphoneStream)
 - Some providers support streaming transcription, where text is returned as it's transcribed
 - For best performance, consider closing or ending the audio stream when you're done with it
 
-## Related Methods
+## Related methods
 
 - [voice.speak()](https://mastra.ai/reference/voice/voice.speak) - Converts text to speech
 - [voice.send()](https://mastra.ai/reference/voice/voice.send) - Sends audio data to the voice provider in real-time