@mastra/voice-openai-realtime 0.1.0-alpha.1 → 0.1.0-alpha.2

package/.turbo/turbo-build.log

@@ -1,23 +1,23 @@
 
-> @mastra/voice-openai-realtime@0.1.0-alpha.1 build /home/runner/work/mastra/mastra/voice/openai-realtime-api
+> @mastra/voice-openai-realtime@0.1.0-alpha.2 build /home/runner/work/mastra/mastra/voice/openai-realtime-api
 > tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake
 
 CLI Building entry: src/index.ts
 CLI Using tsconfig: tsconfig.json
 CLI tsup v8.4.0
 TSC Build start
-TSC ⚡️ Build success in 9409ms
+TSC ⚡️ Build success in 9123ms
 DTS Build start
 CLI Target: es2022
 Analysis will use the bundled TypeScript version 5.8.2
 Writing package typings: /home/runner/work/mastra/mastra/voice/openai-realtime-api/dist/_tsup-dts-rollup.d.ts
 Analysis will use the bundled TypeScript version 5.8.2
 Writing package typings: /home/runner/work/mastra/mastra/voice/openai-realtime-api/dist/_tsup-dts-rollup.d.cts
-DTS ⚡️ Build success in 10803ms
+DTS ⚡️ Build success in 10151ms
 CLI Cleaning output folder
 ESM Build start
 CJS Build start
-CJS dist/index.cjs 17.77 KB
-CJS ⚡️ Build success in 694ms
-ESM dist/index.js 17.72 KB
-ESM ⚡️ Build success in 695ms
+CJS dist/index.cjs 17.80 KB
+CJS ⚡️ Build success in 842ms
+ESM dist/index.js 17.75 KB
+ESM ⚡️ Build success in 843ms

package/CHANGELOG.md

@@ -1,5 +1,15 @@
 # @mastra/voice-openai-realtime
 
+## 0.1.0-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [a838fde]
+- Updated dependencies [a8bd4cf]
+- Updated dependencies [7a3eeb0]
+- Updated dependencies [6530ad1]
+  - @mastra/core@0.7.0-alpha.2
+
 ## 0.1.0-alpha.1
 
 ### Minor Changes

package/dist/index.cjs

@@ -1,10 +1,10 @@
 'use strict';
 
-var voice = require('@mastra/core/voice');
+var events = require('events');
 var stream = require('stream');
-var zodToJsonSchema = require('zod-to-json-schema');
+var voice = require('@mastra/core/voice');
 var ws = require('ws');
-var events = require('events');
+var zodToJsonSchema = require('zod-to-json-schema');
 
 // src/index.ts
 var transformTools = (tools) => {
@@ -65,6 +65,8 @@ var transformTools = (tools) => {
 var isReadableStream = (obj) => {
   return obj && obj instanceof stream.Readable && typeof obj.read === "function" && typeof obj.pipe === "function" && obj.readable === true;
 };
+
+// src/index.ts
 var DEFAULT_VOICE = "alloy";
 var DEFAULT_URL = "wss://api.openai.com/v1/realtime";
 var DEFAULT_MODEL = "gpt-4o-mini-realtime-preview-2024-12-17";
@@ -502,8 +504,8 @@ var OpenAIRealtimeVoice = class extends voice.MastraVoice {
     this.client.on("response.text.done", (ev) => {
       this.emit("writing", { text: "\n", response_id: ev.response_id });
     });
-    this.client.on("response.done", (ev) => {
-      this.handleFunctionCalls(ev);
+    this.client.on("response.done", async (ev) => {
+      await this.handleFunctionCalls(ev);
       this.emit("response.done", ev);
       speakerStreams.delete(ev.response.id);
     });

package/dist/index.js

@@ -1,8 +1,8 @@
-import { MastraVoice } from '@mastra/core/voice';
+import { EventEmitter } from 'events';
 import { PassThrough, Readable } from 'stream';
-import { zodToJsonSchema } from 'zod-to-json-schema';
+import { MastraVoice } from '@mastra/core/voice';
 import { WebSocket } from 'ws';
-import { EventEmitter } from 'events';
+import { zodToJsonSchema } from 'zod-to-json-schema';
 
 // src/index.ts
 var transformTools = (tools) => {
@@ -63,6 +63,8 @@ var transformTools = (tools) => {
 var isReadableStream = (obj) => {
   return obj && obj instanceof Readable && typeof obj.read === "function" && typeof obj.pipe === "function" && obj.readable === true;
 };
+
+// src/index.ts
 var DEFAULT_VOICE = "alloy";
 var DEFAULT_URL = "wss://api.openai.com/v1/realtime";
 var DEFAULT_MODEL = "gpt-4o-mini-realtime-preview-2024-12-17";
@@ -500,8 +502,8 @@ var OpenAIRealtimeVoice = class extends MastraVoice {
     this.client.on("response.text.done", (ev) => {
       this.emit("writing", { text: "\n", response_id: ev.response_id });
     });
-    this.client.on("response.done", (ev) => {
-      this.handleFunctionCalls(ev);
+    this.client.on("response.done", async (ev) => {
+      await this.handleFunctionCalls(ev);
       this.emit("response.done", ev);
       speakerStreams.delete(ev.response.id);
     });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/voice-openai-realtime",
-  "version": "0.1.0-alpha.1",
+  "version": "0.1.0-alpha.2",
   "description": "Mastra OpenAI Realtime API integration",
   "type": "module",
   "main": "dist/index.js",
@@ -22,7 +22,7 @@
     "openai-realtime-api": "^1.0.7",
     "ws": "^8.18.1",
     "zod-to-json-schema": "^3.24.1",
-    "@mastra/core": "^0.7.0-alpha.1"
+    "@mastra/core": "^0.7.0-alpha.2"
   },
   "devDependencies": {
     "@microsoft/api-extractor": "^7.49.2",

package/src/index.ts

@@ -1,10 +1,10 @@
+import { EventEmitter } from 'events';
+import { PassThrough } from 'stream';
 import type { ToolsInput } from '@mastra/core/agent';
 import { MastraVoice } from '@mastra/core/voice';
-import { isReadableStream, transformTools } from './utils';
-import { WebSocket } from 'ws';
-import { EventEmitter } from 'events';
 import type { Realtime, RealtimeServerEvents } from 'openai-realtime-api';
-import { PassThrough } from 'stream';
+import { WebSocket } from 'ws';
+import { isReadableStream, transformTools } from './utils';
 
 /**
  * Event callback function type
@@ -36,21 +36,22 @@ const DEFAULT_URL = 'wss://api.openai.com/v1/realtime';
  * This model is optimized for low-latency responses while maintaining high quality output.
  */
 const DEFAULT_MODEL = 'gpt-4o-mini-realtime-preview-2024-12-17';
-/**
- * Default Voice Activity Detection (VAD) configuration.
- * These settings control how the system detects speech segments.
- *
- * @property {string} type - Uses server-side VAD for better accuracy
- * @property {number} threshold - Speech detection sensitivity (0.5 = balanced)
- * @property {number} prefix_padding_ms - Includes 1 second of audio before speech
- * @property {number} silence_duration_ms - Waits 1 second of silence before ending turn
- */
-const DEFAULT_VAD_CONFIG = {
-  type: 'server_vad',
-  threshold: 0.5,
-  prefix_padding_ms: 1000,
-  silence_duration_ms: 1000,
-} as Realtime.TurnDetection;
+
+// /**
+//  * Default Voice Activity Detection (VAD) configuration.
+//  * These settings control how the system detects speech segments.
+//  *
+//  * @property {string} type - Uses server-side VAD for better accuracy
+//  * @property {number} threshold - Speech detection sensitivity (0.5 = balanced)
+//  * @property {number} prefix_padding_ms - Includes 1 second of audio before speech
+//  * @property {number} silence_duration_ms - Waits 1 second of silence before ending turn
+//  */
+// const DEFAULT_VAD_CONFIG = {
+//   type: 'server_vad',
+//   threshold: 0.5,
+//   prefix_padding_ms: 1000,
+//   silence_duration_ms: 1000,
+// } as Realtime.TurnDetection;
 
 type TTools = ToolsInput;
 
@@ -580,8 +581,8 @@ export class OpenAIRealtimeVoice extends MastraVoice {
     this.client.on('response.text.done', ev => {
       this.emit('writing', { text: '\n', response_id: ev.response_id });
     });
-    this.client.on('response.done', ev => {
-      this.handleFunctionCalls(ev);
+    this.client.on('response.done', async ev => {
+      await this.handleFunctionCalls(ev);
       this.emit('response.done', ev);
       speakerStreams.delete(ev.response.id);
     });