feat(xsAI): add xsAI voice provider

.changeset/xsai-voice-provider.md

@@ -0,0 +1,11 @@
+---
+"@voltagent/voice": minor
+---
+
+feat(xsAI): add xsAI voice provider
+
+This adds support for the xsAI voice provider, including:
+
+- Core provider implementation support
+- Support for API key authentication and custom headers
+- Base URL configuration for API endpoints

examples/with-voice-xsai/.gitignore

@@ -0,0 +1,4 @@
+node_modules
+dist
+.DS_Store
+.env 

examples/with-voice-xsai/README.md

@@ -0,0 +1,53 @@
+<div align="center">
+<a href="https://voltagent.dev/">
+<img width="1800" alt="435380213-b6253409-8741-462b-a346-834cd18565a9" src="https://github.com/user-attachments/assets/452a03e7-eeda-4394-9ee7-0ffbcf37245c" />
+</a>
+
+<br/>
+<br/>
+
+<div align="center">
+    <a href="https://voltagent.dev">Home Page</a> |
+    <a href="https://voltagent.dev/docs/">Documentation</a> |
+    <a href="https://github.com/voltagent/voltagent/tree/main/examples">Examples</a> |
+    <a href="https://s.voltagent.dev/discord">Discord</a> |
+    <a href="https://voltagent.dev/blog/">Blog</a>
+</div>
+</div>
+
+<br/>
+
+<div align="center">
+    <strong>VoltAgent is an open source TypeScript framework for building and orchestrating AI agents.</strong><br>
+Escape the limitations of no-code builders and the complexity of starting from scratch.
+    <br />
+    <br />
+</div>
+
+<div align="center">
+
+[![npm version](https://img.shields.io/npm/v/@voltagent/core.svg)](https://www.npmjs.com/package/@voltagent/core)
+[![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-2.0-4baaaa.svg)](CODE_OF_CONDUCT.md)
+[![Discord](https://img.shields.io/discord/1361559153780195478.svg?label=&logo=discord&logoColor=ffffff&color=7389D8&labelColor=6A7EC2)](https://s.voltagent.dev/discord)
+[![Twitter Follow](https://img.shields.io/twitter/follow/voltagent_dev?style=social)](https://twitter.com/voltagent_dev)
+
+</div>
+
+<br/>
+
+<div align="center">
+<a href="https://voltagent.dev/">
+<img width="896" alt="VoltAgent Schema" src="https://github.com/user-attachments/assets/f0627868-6153-4f63-ba7f-bdfcc5dd603d" />
+</a>
+
+</div>
+
+## VoltAgent: Build AI Agents Fast and Flexibly
+
+VoltAgent is an open-source TypeScript framework for creating and managing AI agents. It provides modular components to build, customize, and scale agents with ease. From connecting to APIs and memory management to supporting multiple LLMs, VoltAgent simplifies the process of creating sophisticated AI systems. It enables fast development, maintains clean code, and offers flexibility to switch between models and tools without vendor lock-in.
+
+## Try Example
+
+```bash
+npm create voltagent-app@latest -- --example with-voice-xsai
+```

examples/with-voice-xsai/package.json

@@ -0,0 +1,35 @@
+{
+  "name": "voltagent-example-with-voice-xsai",
+  "private": true,
+  "keywords": [
+    "voltagent",
+    "ai",
+    "agent",
+    "voice",
+    "xsai"
+  ],
+  "license": "MIT",
+  "author": "",
+  "type": "module",
+  "scripts": {
+    "build": "tsc",
+    "dev": "tsx watch --env-file=.env ./src ",
+    "start": "node dist/index.js",
+    "volt": "volt"
+  },
+  "dependencies": {
+    "@ai-sdk/openai": "^1.3.10",
+    "@voltagent/cli": "^0.1.4",
+    "@voltagent/core": "^0.1.12",
+    "@voltagent/vercel-ai": "^0.1.5",
+    "@voltagent/voice": "^0.1.4",
+    "dotenv": "^16.4.5",
+    "openai": "^4.91.0",
+    "zod": "^3.24.2"
+  },
+  "devDependencies": {
+    "@types/node": "^22.13.5",
+    "tsx": "^4.19.3",
+    "typescript": "^5.8.2"
+  }
+}

examples/with-voice-xsai/src/index.ts

@@ -0,0 +1,65 @@
+import { join } from "path";
+import { createReadStream, createWriteStream } from "fs";
+import { VercelAIProvider } from "@voltagent/vercel-ai";
+import { VoltAgent, Agent } from "@voltagent/core";
+import { XsAIVoiceProvider } from "@voltagent/voice";
+import { openai } from "@ai-sdk/openai";
+
+const voiceProvider = new XsAIVoiceProvider({
+  apiKey: process.env.OPENAI_API_KEY!,
+});
+
+const agent = new Agent({
+  name: "Voice Assistant",
+  description: "Speaks & listens via xsAI",
+  llm: new VercelAIProvider(),
+  model: openai("gpt-4o-mini"),
+  voice: voiceProvider,
+});
+
+// Create the VoltAgent with our voice-enabled agent
+new VoltAgent({
+  agents: {
+    agent,
+  },
+});
+
+(async () => {
+  const voices = await agent.voice?.getVoices();
+  console.log("Available voices:", voices);
+
+  const audioStream = await agent.voice?.speak(
+    "Hello, VoltAgent is best framework for building voice agents! Yeah!",
+    {
+      speed: 1.0,
+    },
+  );
+
+  console.log("audioStream", audioStream);
+
+  // Save the audio stream to a file (for demonstration)
+  const outputPath = join(process.cwd(), "output.mp3");
+  const writeStream = createWriteStream(outputPath);
+  audioStream?.pipe(writeStream);
+  console.log("Audio saved to:", outputPath);
+
+  const audioFile = createReadStream(outputPath);
+  const transcribedText = await agent.voice?.listen(audioFile, {
+    language: "en",
+    stream: false,
+  });
+  console.log("Transcribed text:", transcribedText);
+})();
+
+// Event listeners for voice interactions
+voiceProvider.on("speaking", (event: { text: string }) => {
+  console.log(`Speaking: ${event.text.substring(0, 50)}...`);
+});
+
+voiceProvider.on("listening", () => {
+  console.log("Listening to audio input...");
+});
+
+voiceProvider.on("error", (error: { message: string }) => {
+  console.error("Voice error:", error.message);
+});

examples/with-voice-xsai/tsconfig.json

@@ -0,0 +1,14 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "NodeNext",
+    "moduleResolution": "NodeNext",
+    "esModuleInterop": true,
+    "forceConsistentCasingInFileNames": true,
+    "strict": true,
+    "outDir": "dist",
+    "skipLibCheck": true
+  },
+  "include": ["src"],
+  "exclude": ["node_modules", "dist"]
+}

packages/voice/package.json

@@ -24,6 +24,8 @@
   },
   "dependencies": {
     "@voltagent/core": "^0.1.8",
+    "@xsai/generate-speech": "^0.2.0",
+    "@xsai/generate-transcription": "^0.2.0",
     "elevenlabs": "^1.55.0",
     "openai": "^4.91.0"
   },

packages/voice/src/index.ts

@@ -2,3 +2,4 @@ export * from "./types";
 export * from "./providers/base";
 export * from "./providers/openai";
 export * from "./providers/elevenlabs";
+export * from "./providers/xsai";

packages/voice/src/providers/xsai/index.ts

@@ -0,0 +1,149 @@
+import { PassThrough } from "node:stream";
+import type { VoiceMetadata, ReadableStreamType } from "@voltagent/core";
+import { BaseVoiceProvider } from "../base";
+import { XsaiVoiceOptions, XsaiSpeakOptions, XsaiListenOptions } from "./types";
+import { generateSpeech, GenerateSpeechOptions } from "@xsai/generate-speech";
+import { generateTranscription, GenerateTranscriptionOptions } from "@xsai/generate-transcription";
+
+/* ------------------------------------------------------------------ */
+/*  Helper: bufferise a Node stream                                   */
+/* ------------------------------------------------------------------ */
+async function collectChunks(stream: NodeJS.ReadableStream): Promise<Buffer> {
+  const chunks: Buffer[] = [];
+  for await (const c of stream) {
+    chunks.push(typeof c === "string" ? Buffer.from(c) : c);
+  }
+  return Buffer.concat(chunks);
+}
+
+/* ------------------------------------------------------------------ */
+/*  xsAI provider                                                     */
+/* ------------------------------------------------------------------ */
+export class XsAIVoiceProvider extends BaseVoiceProvider {
+  private readonly apiKey: string;
+  private readonly baseURL: string;
+  private readonly ttsModel: string;
+  private readonly speechModel: string;
+  private readonly voice: string;
+  private readonly headers?: Record<string, string>;
+
+  constructor(options: XsaiVoiceOptions) {
+    super(options);
+
+    this.apiKey = options.apiKey;
+    this.baseURL = options.baseURL ?? "https://api.openai.com/v1";
+    this.ttsModel = options.ttsModel ?? "tts-1";
+    this.speechModel = options.speechModel ?? "whisper-1";
+    this.voice = options.voice ?? "alloy";
+    this.headers = options.options?.headers;
+  }
+
+  /* ------------------------------------------------------------------ */
+  /*  TEXT ➜ SPEECH                                                     */
+  /* ------------------------------------------------------------------ */
+  async speak(
+    input: string | NodeJS.ReadableStream,
+    opts: XsaiSpeakOptions = {},
+  ): Promise<NodeJS.ReadableStream> {
+    try {
+      const text =
+        typeof input === "string" ? input : (await collectChunks(input)).toString("utf8");
+
+      if (!text.trim()) throw new Error("Input text is empty");
+      this.emit("speaking", { text });
+
+      // Dynamically import the module
+
+      const generateSpeechOptions: GenerateSpeechOptions = {
+        input: text,
+        voice: opts.voice ?? this.voice ?? "default",
+        responseFormat: opts.format ?? "mp3",
+        speed: opts.speed ?? 1.0,
+        /* CommonRequestOptions */
+        apiKey: this.apiKey,
+        baseURL: this.baseURL,
+        model: this.ttsModel,
+        headers: this.headers,
+      };
+
+      const arrayBuf = await generateSpeech(generateSpeechOptions);
+
+      const stream = new PassThrough();
+      stream.end(Buffer.from(arrayBuf));
+      return stream;
+    } catch (err) {
+      this.emit("error", {
+        message: err instanceof Error ? err.message : "Unknown error",
+        code: "SPEAK_ERROR",
+        details: err,
+      });
+      throw err;
+    }
+  }
+
+  /* ------------------------------------------------------------------ */
+  /*  SPEECH ➜ TEXT                                                     */
+  /* ------------------------------------------------------------------ */
+  async listen(
+    audio: NodeJS.ReadableStream,
+    opts: XsaiListenOptions = {},
+  ): Promise<string | ReadableStreamType> {
+    try {
+      this.emit("listening", { audio });
+      const buf = await collectChunks(audio);
+
+      const blob = new Blob([buf]);
+
+      const generateTranscriptionOptions: GenerateTranscriptionOptions = {
+        file: blob,
+        fileName: opts.fileName ?? "audio.wav",
+        language: opts.language,
+        prompt: opts.prompt,
+        temperature: opts.temperature,
+        /* CommonRequestOptions */
+        apiKey: this.apiKey,
+        baseURL: this.baseURL,
+        model: this.speechModel,
+        headers: this.headers,
+      };
+
+      const { text } = await generateTranscription(generateTranscriptionOptions);
+
+      return text;
+    } catch (err) {
+      this.emit("error", {
+        message: err instanceof Error ? err.message : "Unknown error",
+        code: "LISTEN_ERROR",
+        details: err,
+      });
+      throw err;
+    }
+  }
+
+  /* ------------------------------------------------------------------ */
+  /*  Real‑time streaming not yet available                             */
+  /* ------------------------------------------------------------------ */
+  async connect(): Promise<void> {
+    throw new Error("Real‑time streaming not supported by xsAI");
+  }
+  disconnect(): void {
+    /* noop */
+  }
+  async send(): Promise<void> {
+    throw new Error("Real‑time streaming not supported by xsAI");
+  }
+
+  /* ------------------------------------------------------------------ */
+  /*  xsAI hasn't published a voice list API – stub with default        */
+  /* ------------------------------------------------------------------ */
+  async getVoices(): Promise<VoiceMetadata[]> {
+    return [
+      {
+        id: this.voice ?? "default",
+        name: "xsAI default",
+        language: "en",
+        gender: "neutral",
+      },
+    ];
+  }
+}