Add Athena Whisper dictation provider to OpenClaw Talk plugin

2026-09-16 15:20:38 +02:00
parent 1c93b9c7c1
commit ba68d4e8fb
8 changed files with 257 additions and 3 deletions
@@ -0,0 +1,59 @@
+import assert from "node:assert/strict";
+import { createServer } from "node:http";
+import { test } from "node:test";
+import plugin from "./dist/index.js";
+
+test("dictation registers separately and sends G.711 audio to Athena Whisper", async () => {
+  let transcription;
+  plugin.register({
+    registerRealtimeTranscriptionProvider: (value) => { transcription = value; },
+    registerRealtimeVoiceProvider: () => {},
+    registerHttpRoute: () => {},
+  });
+  assert.equal(transcription.id, "athena-talk");
+
+  let uploads = 0;
+  const server = createServer(async (req, res) => {
+    uploads += 1;
+    assert.equal(req.url, "/v1/audio/transcriptions");
+    assert.equal(req.headers.authorization, "Bearer test-key");
+    const form = await new Request("http://localhost", {
+      method: "POST",
+      headers: { "Content-Type": req.headers["content-type"] },
+      body: req,
+      duplex: "half",
+    }).formData();
+    const wav = Buffer.from(await form.get("file").arrayBuffer());
+    assert.equal(wav.toString("ascii", 0, 4), "RIFF");
+    assert.equal(wav.readUInt32LE(24), 8000);
+    assert.equal(wav.readUInt16LE(34), 16);
+    assert.equal(wav.length, 48);
+    assert.equal(form.get("language"), "de");
+    assert.equal(form.get("model"), "whisper-1");
+    res.writeHead(200, { "Content-Type": "application/json" }).end(JSON.stringify({ text: "Hallo Athena" }));
+  });
+  await new Promise((resolve) => server.listen(0, "127.0.0.1", resolve));
+  const cfg = { talk: { realtime: { providers: { "athena-talk": {
+    baseUrl: `http://127.0.0.1:${server.address().port}/v1`, apiKey: "test-key", language: "de",
+  } } } } };
+  const providerConfig = transcription.resolveConfig({ cfg, rawConfig: {} });
+  assert.equal(transcription.isConfigured({ cfg, providerConfig }), true);
+  try {
+    const result = new Promise((resolve, reject) => {
+      const session = transcription.createSession({
+        cfg, providerConfig,
+        onTranscript: resolve,
+        onError: reject,
+      });
+      session.connect().then(() => {
+        session.sendAudio(Buffer.from([0xff, 0xff]));
+        session.close();
+      }, reject);
+    });
+    assert.equal(await result, "Hallo Athena");
+    assert.equal(uploads, 1);
+  } finally {
+    server.closeAllConnections();
+    await new Promise((resolve) => server.close(resolve));
+  }
+});