Merge pull request #60 from AssemblyAI/E07417BDFEA3614F5967B1520F8B2F61

Sync from internal repo (2024/06/21)

.eslintrc.json

@@ -9,7 +9,7 @@
   "rules": {
     "tsdoc/syntax": "warn"
   },
-  "ignorePatterns": ["/*.js", "/*.ts", "dist", "node_modules"],
+  "ignorePatterns": ["/*.js", "/*.ts", "samples", "dist", "node_modules"],
   "overrides": [
     {
       "files": ["tests/**/*"],

samples/streaming-stt-from-mic/.env.sample

@@ -0,0 +1 @@
+ASSEMBLYAI_API_KEY=[YOUR_ASSEMBLYAI_API_KEY]

samples/streaming-stt-from-mic/README.md

@@ -0,0 +1,30 @@
+# Transcribe streaming audio from a microphone in TypeScript
+
+This sample lets you transcribe audio from your microphone in real time using AssemblyAI Streaming Speech-to-Text.
+For step-by-step instructions on how to build this sample yourself, see [Transcribe streaming audio from a microphone in TypeScript](https://www.assemblyai.com/docs/getting-started/transcribe-streaming-audio-from-a-microphone/typescript).
+
+To run the sample, you'll need the following:
+
+- [Node.js](https://nodejs.org/)
+- [SoX](https://sourceforge.net/projects/sox/)
+- An AssemblyAI account with a credit card set up
+
+Install the dependencies:
+
+```bash
+npm install
+```
+
+Configure the `ASSEMBLYAI_API_KEY` environment variable in your shell, or create a `.env` file with the following contents and replace `[YOUR_ASSEMBLYAI_API_KEY]` with your API key:
+
+```plaintext
+ASSEMBLYAI_API_KEY=[YOUR_ASSEMBLYAI_API_KEY]
+```
+
+Run the sample:
+
+```bash
+npm run start
+```
+
+Credits: `sox.ts` is adapted from the [node-record-lpcm16](https://github.com/gillesdemey/node-record-lpcm16) project by Gilles De Mey.

samples/streaming-stt-from-mic/index.js

@@ -0,0 +1,47 @@
+import "dotenv/config";
+import { AssemblyAI } from "assemblyai";
+import { SoxRecording } from "./sox.js";
+const SAMPLE_RATE = 16000;
+const client = new AssemblyAI({
+  apiKey: process.env.ASSEMBLYAI_API_KEY,
+});
+const transcriber = client.realtime.transcriber({
+  sampleRate: SAMPLE_RATE,
+});
+transcriber.on("open", ({ sessionId }) => {
+  console.log(`Session opened with ID: ${sessionId}`);
+});
+transcriber.on("error", (error) => {
+  console.error("Error:", error);
+});
+transcriber.on("close", (code, reason) =>
+  console.log("Session closed:", code, reason),
+);
+transcriber.on("transcript", (transcript) => {
+  if (!transcript.text) {
+    return;
+  }
+  if (transcript.message_type === "PartialTranscript") {
+    console.log("Partial:", transcript.text);
+  } else {
+    console.log("Final:", transcript.text);
+  }
+});
+console.log("Connecting to real-time transcript service");
+await transcriber.connect();
+console.log("Starting recording");
+const recording = new SoxRecording({
+  channels: 1,
+  sampleRate: SAMPLE_RATE,
+  audioType: "wav", // Linear PCM
+});
+recording.stream().pipeTo(transcriber.stream());
+// Stop recording and close connection using Ctrl-C.
+process.on("SIGINT", async function () {
+  console.log();
+  console.log("Stopping recording");
+  recording.stop();
+  console.log("Closing real-time transcript connection");
+  await transcriber.close();
+  process.exit();
+});

samples/streaming-stt-from-mic/index.ts

@@ -0,0 +1,61 @@
+import "dotenv/config";
+import { AssemblyAI, RealtimeTranscript } from "assemblyai";
+import { SoxRecording } from "./sox.js";
+
+const SAMPLE_RATE = 16_000;
+
+const client = new AssemblyAI({
+  apiKey: process.env.ASSEMBLYAI_API_KEY!,
+});
+
+const transcriber = client.realtime.transcriber({
+  sampleRate: SAMPLE_RATE,
+});
+
+transcriber.on("open", ({ sessionId }) => {
+  console.log(`Session opened with ID: ${sessionId}`);
+});
+
+transcriber.on("error", (error: Error) => {
+  console.error("Error:", error);
+});
+
+transcriber.on("close", (code: number, reason: string) =>
+  console.log("Session closed:", code, reason),
+);
+
+transcriber.on("transcript", (transcript: RealtimeTranscript) => {
+  if (!transcript.text) {
+    return;
+  }
+
+  if (transcript.message_type === "PartialTranscript") {
+    console.log("Partial:", transcript.text);
+  } else {
+    console.log("Final:", transcript.text);
+  }
+});
+
+console.log("Connecting to real-time transcript service");
+await transcriber.connect();
+
+console.log("Starting recording");
+const recording = new SoxRecording({
+  channels: 1,
+  sampleRate: SAMPLE_RATE,
+  audioType: "wav", // Linear PCM
+});
+
+recording.stream().pipeTo(transcriber.stream());
+
+// Stop recording and close connection using Ctrl-C.
+process.on("SIGINT", async function () {
+  console.log();
+  console.log("Stopping recording");
+  recording.stop();
+
+  console.log("Closing real-time transcript connection");
+  await transcriber.close();
+
+  process.exit();
+});