@mastra/voice-openai 0.12.1 → 0.12.2

package/dist/docs/references/reference-voice-voice.listen.md

@@ -4,11 +4,11 @@ The `listen()` method is a core function available in all Mastra voice providers
 
 ## Parameters
 
-**audioStream:** (`NodeJS.ReadableStream`): Audio stream to transcribe. This can be a file stream or a microphone stream.
+**audioStream** (`NodeJS.ReadableStream`): Audio stream to transcribe. This can be a file stream or a microphone stream.
 
-**options?:** (`object`): Provider-specific options for speech recognition
+**options** (`object`): Provider-specific options for speech recognition
 
-## Return Value
+## Return value
 
 Returns one of the following:
 
@@ -16,81 +16,87 @@ 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.prompt?:** (`string`): Text to guide the model's transcription
+**options.filetype** (`string`): Audio file format (e.g., 'mp3', 'wav', 'm4a')
 
-**options.language?:** (`string`): Language code (e.g., 'en', 'fr', 'de')
+**options.prompt** (`string`): Text to guide the model's transcription
+
+**options.language** (`string`): Language code (e.g., 'en', 'fr', 'de')
 
 ### 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.language?:** (`string`): Language code for transcription (Default: `'en'`)
+**options.model** (`string`): Deepgram model to use for transcription
 
-## Usage Example
+**options.language** (`string`): Language code for transcription
+
+## Usage example
 
 ```typescript
-import { OpenAIVoice } from "@mastra/voice-openai";
-import { getMicrophoneStream } from "@mastra/node-audio";
-import { createReadStream } from "fs";
-import path from "path";
+import { OpenAIVoice } from '@mastra/voice-openai'
+import { getMicrophoneStream } from '@mastra/node-audio'
+import { createReadStream } from 'fs'
+import path from 'path'
 
 // Initialize a voice provider
 const voice = new OpenAIVoice({
   listeningModel: {
-    name: "whisper-1",
+    name: 'whisper-1',
     apiKey: process.env.OPENAI_API_KEY,
   },
-});
+})
 
 // Basic usage with a file stream
-const audioFilePath = path.join(process.cwd(), "audio.mp3");
-const audioStream = createReadStream(audioFilePath);
+const audioFilePath = path.join(process.cwd(), 'audio.mp3')
+const audioStream = createReadStream(audioFilePath)
 const transcript = await voice.listen(audioStream, {
-  filetype: "mp3",
-});
-console.log("Transcribed text:", transcript);
+  filetype: 'mp3',
+})
+console.log('Transcribed text:', transcript)
 
 // Using a microphone stream
-const microphoneStream = getMicrophoneStream(); // Assume this function gets audio input
-const transcription = await voice.listen(microphoneStream);
+const microphoneStream = getMicrophoneStream() // Assume this function gets audio input
+const transcription = await voice.listen(microphoneStream)
 
 // With provider-specific options
 const transcriptWithOptions = await voice.listen(audioStream, {
-  language: "en",
-  prompt: "This is a conversation about artificial intelligence.",
-});
+  language: 'en',
+  prompt: 'This is a conversation about artificial intelligence.',
+})
 ```
 
-## Using with CompositeVoice
+## Using with `CompositeVoice`
 
 When using `CompositeVoice`, the `listen()` method delegates to the configured listening provider:
 
 ```typescript
-import { CompositeVoice } from "@mastra/core/voice";
-import { OpenAIVoice } from "@mastra/voice-openai";
-import { PlayAIVoice } from "@mastra/voice-playai";
+import { CompositeVoice } from '@mastra/core/voice'
+import { OpenAIVoice } from '@mastra/voice-openai'
+import { PlayAIVoice } from '@mastra/voice-playai'
 
 const voice = new CompositeVoice({
   input: new OpenAIVoice(),
   output: new PlayAIVoice(),
-});
+})
 
 // This will use the OpenAIVoice provider
-const transcript = await voice.listen(audioStream);
+const transcript = await voice.listen(audioStream)
 ```
 
 ### Using AI SDK Model Providers
@@ -98,18 +104,18 @@ const transcript = await voice.listen(audioStream);
 You can also use AI SDK transcription models directly with `CompositeVoice`:
 
 ```typescript
-import { CompositeVoice } from "@mastra/core/voice";
-import { openai } from "@ai-sdk/openai";
-import { groq } from "@ai-sdk/groq";
+import { CompositeVoice } from '@mastra/core/voice'
+import { openai } from '@ai-sdk/openai'
+import { groq } from '@ai-sdk/groq'
 
 // Use AI SDK transcription models
 const voice = new CompositeVoice({
-  input: openai.transcription('whisper-1'),  // AI SDK model
-  output: new PlayAIVoice(),                 // Mastra provider
-});
+  input: openai.transcription('whisper-1'), // AI SDK model
+  output: new PlayAIVoice(), // Mastra provider
+})
 
 // Works the same way
-const transcript = await voice.listen(audioStream);
+const transcript = await voice.listen(audioStream)
 
 // Provider-specific options can be passed through
 const transcriptWithOptions = await voice.listen(audioStream, {
@@ -117,14 +123,14 @@ const transcriptWithOptions = await voice.listen(audioStream, {
     openai: {
       language: 'en',
       prompt: 'This is about AI',
-    }
-  }
-});
+    },
+  },
+})
 ```
 
 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:
 
@@ -132,20 +138,20 @@ When using realtime voice providers like `OpenAIRealtimeVoice`, the `listen()` m
 - You need to register an event listener to receive the transcription
 
 ```typescript
-import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
-import { getMicrophoneStream } from "@mastra/node-audio";
+import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
+import { getMicrophoneStream } from '@mastra/node-audio'
 
-const voice = new OpenAIRealtimeVoice();
-await voice.connect();
+const voice = new OpenAIRealtimeVoice()
+await voice.connect()
 
 // Register event listener for transcription
-voice.on("writing", ({ text, role }) => {
-  console.log(`${role}: ${text}`);
-});
+voice.on('writing', ({ text, role }) => {
+  console.log(`${role}: ${text}`)
+})
 
 // This will emit 'writing' events instead of returning text
-const microphoneStream = getMicrophoneStream();
-await voice.listen(microphoneStream);
+const microphoneStream = getMicrophoneStream()
+await voice.listen(microphoneStream)
 ```
 
 ## Notes
@@ -157,8 +163,8 @@ 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
-- [voice.on()](https://mastra.ai/reference/voice/voice.on) - Registers an event listener for voice events
+- [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
+- [voice.on()](https://mastra.ai/reference/voice/voice.on): Registers an event listener for voice events

package/dist/docs/references/reference-voice-voice.speak.md

@@ -4,88 +4,98 @@ The `speak()` method is a core function available in all Mastra voice providers
 
 ## Parameters
 
-**input:** (`string | NodeJS.ReadableStream`): Text to convert to speech. Can be a string or a readable stream of text.
+**input** (`string | NodeJS.ReadableStream`): Text to convert to speech. Can be a string or a readable stream of text.
 
-**options?:** (`object`): Options for speech synthesis
+**options** (`object`): Options for speech synthesis
 
-**options.speaker?:** (`string`): Voice ID to use for this specific request. Overrides the default speaker set in the constructor.
+**options.speaker** (`string`): Voice ID to use for this specific request. Overrides the default speaker set in the constructor.
 
-## Return Value
+## Return value
 
 Returns a `Promise<NodeJS.ReadableStream | void>` where:
 
 - `NodeJS.ReadableStream`: A stream of audio data that can be played or saved
 - `void`: When using a realtime voice provider that emits audio through events instead of returning it directly
 
-## Provider-Specific Options
+## Provider-specific options
 
 Each voice provider may support additional options specific to their implementation. Here are some examples:
 
 ### OpenAI
 
-**options.speed?:** (`number`): Speech speed multiplier. Values between 0.25 and 4.0 are supported. (Default: `1.0`)
+**options** (`Options`): Configuration options.
+
+**options.speed** (`number`): Speech speed multiplier. Values between 0.25 and 4.0 are supported.
 
 ### ElevenLabs
 
-**options.stability?:** (`number`): Voice stability. Higher values result in more stable, less expressive speech. (Default: `0.5`)
+**options** (`Options`): Configuration options.
+
+**options.stability** (`number`): Voice stability. Higher values result in more stable, less expressive speech.
 
-**options.similarity\_boost?:** (`number`): Voice clarity and similarity to the original voice. (Default: `0.75`)
+**options.similarity\_boost** (`number`): Voice clarity and similarity to the original voice.
 
 ### Google
 
-**options.languageCode?:** (`string`): Language code for the voice (e.g., 'en-US').
+**options** (`Options`): Configuration options.
+
+**options.languageCode** (`string`): Language code for the voice (e.g., 'en-US').
 
-**options.audioConfig?:** (`object`): Audio configuration options from Google Cloud Text-to-Speech API. (Default: `{ audioEncoding: 'LINEAR16' }`)
+**options.audioConfig** (`object`): Audio configuration options from Google Cloud Text-to-Speech API.
 
 ### Murf
 
-**options.properties.rate?:** (`number`): Speech rate multiplier.
+**options** (`Options`): Configuration options.
+
+**options.properties** (`object`): properties configuration.
+
+**options.properties.rate** (`number`): Speech rate multiplier.
 
-**options.properties.pitch?:** (`number`): Voice pitch adjustment.
+**options.properties.pitch** (`number`): Voice pitch adjustment.
 
-**options.properties.format?:** (`'MP3' | 'WAV' | 'FLAC' | 'ALAW' | 'ULAW'`): Output audio format.
+**options.properties.format** (`'MP3' | 'WAV' | 'FLAC' | 'ALAW' | 'ULAW'`): Output audio format.
 
-## Usage Example
+## Usage example
 
 ```typescript
-import { OpenAIVoice } from "@mastra/voice-openai";
+import { OpenAIVoice } from '@mastra/voice-openai'
 // Initialize a voice provider
 const voice = new OpenAIVoice({
-  speaker: "alloy", // Default voice
-});
+  speaker: 'alloy', // Default voice
+})
 // Basic usage with default settings
-const audioStream = await voice.speak("Hello, world!");
+const audioStream = await voice.speak('Hello, world!')
 // Using a different voice for this specific request
-const audioStreamWithDifferentVoice = await voice.speak("Hello again!", {
-  speaker: "nova",
-});
+const audioStreamWithDifferentVoice = await voice.speak('Hello again!', {
+  speaker: 'nova',
+})
 // Using provider-specific options
-const audioStreamWithOptions = await voice.speak("Hello with options!", {
-  speaker: "echo",
+const audioStreamWithOptions = await voice.speak('Hello with options!', {
+  speaker: 'echo',
   speed: 1.2, // OpenAI-specific option
-});
+})
 // Using a text stream as input
-import { Readable } from "stream";
-const textStream = Readable.from(["Hello", " from", " a", " stream!"]);
-const audioStreamFromTextStream = await voice.speak(textStream);
+import { Readable } from 'stream'
+const textStream = Readable.from(['Hello', ' from', ' a', ' stream!'])
+const audioStreamFromTextStream = await voice.speak(textStream)
 ```
 
-## Using with CompositeVoice
+## Using with `CompositeVoice`
 
 When using `CompositeVoice`, the `speak()` method delegates to the configured speaking provider:
 
 ```typescript
-import { CompositeVoice } from "@mastra/core/voice";
-import { OpenAIVoice } from "@mastra/voice-openai";
-import { PlayAIVoice } from "@mastra/voice-playai";
+import { CompositeVoice } from '@mastra/core/voice'
+import { OpenAIVoice } from '@mastra/voice-openai'
+import { PlayAIVoice } from '@mastra/voice-playai'
 
 const voice = new CompositeVoice({
   output: new PlayAIVoice(),
   input: new OpenAIVoice(),
-});
+})
 
 // This will use the PlayAIVoice provider
-const audioStream = await voice.speak("Hello, world!");
+const audioStream = await voice.speak('Hello, world!')
 ```
 
 ### Using AI SDK Model Providers
@@ -93,34 +103,34 @@ const audioStream = await voice.speak("Hello, world!");
 You can also use AI SDK speech models directly with `CompositeVoice`:
 
 ```typescript
-import { CompositeVoice } from "@mastra/core/voice";
-import { openai } from "@ai-sdk/openai";
-import { elevenlabs } from "@ai-sdk/elevenlabs";
+import { CompositeVoice } from '@mastra/core/voice'
+import { openai } from '@ai-sdk/openai'
+import { elevenlabs } from '@ai-sdk/elevenlabs'
 
 // Use AI SDK speech models
 const voice = new CompositeVoice({
-  output: elevenlabs.speech('eleven_turbo_v2'),  // AI SDK model
-  input: openai.transcription('whisper-1'),      // AI SDK model
-});
+  output: elevenlabs.speech('eleven_turbo_v2'), // AI SDK model
+  input: openai.transcription('whisper-1'), // AI SDK model
+})
 
 // Works the same way
-const audioStream = await voice.speak("Hello from AI SDK!");
+const audioStream = await voice.speak('Hello from AI SDK!')
 
 // Provider-specific options can be passed through
-const audioWithOptions = await voice.speak("Hello with options!", {
-  speaker: 'Rachel',  // ElevenLabs voice
+const audioWithOptions = await voice.speak('Hello with options!', {
+  speaker: 'Rachel', // ElevenLabs voice
   providerOptions: {
     elevenlabs: {
       stability: 0.5,
       similarity_boost: 0.75,
-    }
-  }
-});
+    },
+  },
+})
 ```
 
 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 `speak()` method behaves differently:
 
@@ -128,24 +138,24 @@ When using realtime voice providers like `OpenAIRealtimeVoice`, the `speak()` me
 - You need to register an event listener to receive the audio chunks
 
 ```typescript
-import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
-import Speaker from "@mastra/node-speaker";
+import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'
+import Speaker from '@mastra/node-speaker'
 
 const speaker = new Speaker({
   sampleRate: 24100, // Audio sample rate in Hz - standard for high-quality audio on MacBook Pro
   channels: 1, // Mono audio output (as opposed to stereo which would be 2)
   bitDepth: 16, // Bit depth for audio quality - CD quality standard (16-bit resolution)
-});
+})
 
-const voice = new OpenAIRealtimeVoice();
-await voice.connect();
+const voice = new OpenAIRealtimeVoice()
+await voice.connect()
 // Register event listener for audio chunks
-voice.on("speaker", (stream) => {
+voice.on('speaker', stream => {
   // Handle audio chunk (e.g., play it or save it)
-  stream.pipe(speaker);
-});
+  stream.pipe(speaker)
+})
 // This will emit 'speaking' events instead of returning a stream
-await voice.speak("Hello, this is realtime speech!");
+await voice.speak('Hello, this is realtime speech!')
 ```
 
 ## Notes