feat(36-03): add voice HTTP routes with POST /transcribe and POST /synthesize
- Create server/src/routes/voice.ts with voiceRoutes() factory - POST /transcribe: multer audio upload → VoicePipelineService.transcribe → JSON response - POST /synthesize: text body → VoicePipelineService.synthesize → audio/wav response - Both routes protected by assertBoard(req) auth check - Create server/src/__tests__/36-voice-routes.test.ts with 5 passing tests
This commit is contained in:
parent
e76c52f693
commit
bf757509ef
2 changed files with 150 additions and 0 deletions
103
server/src/__tests__/36-voice-routes.test.ts
Normal file
103
server/src/__tests__/36-voice-routes.test.ts
Normal file
|
|
@ -0,0 +1,103 @@
|
||||||
|
import { describe, it, expect, vi, beforeEach } from "vitest";
|
||||||
|
import express from "express";
|
||||||
|
import supertest from "supertest";
|
||||||
|
|
||||||
|
// Mock voicePipelineService BEFORE importing voice routes
|
||||||
|
vi.mock("../services/voice-pipeline.js", () => ({
|
||||||
|
voicePipelineService: vi.fn(() => ({
|
||||||
|
transcribe: vi.fn().mockResolvedValue({ text: "Hello world", language: "en" }),
|
||||||
|
synthesize: vi.fn().mockResolvedValue(Buffer.from("fake-wav-audio")),
|
||||||
|
formatForVoice: vi.fn((t: string) => t),
|
||||||
|
transcodeToWav16k: vi.fn().mockResolvedValue(Buffer.from("wav-data")),
|
||||||
|
})),
|
||||||
|
}));
|
||||||
|
|
||||||
|
// Mock assertBoard to be a no-op (board auth passes)
|
||||||
|
vi.mock("../routes/authz.js", () => ({
|
||||||
|
assertBoard: vi.fn(),
|
||||||
|
}));
|
||||||
|
|
||||||
|
import { voiceRoutes } from "../routes/voice.js";
|
||||||
|
|
||||||
|
function buildApp() {
|
||||||
|
const app = express();
|
||||||
|
app.use(express.json());
|
||||||
|
|
||||||
|
// Attach a mock actor so assertBoard sees board type
|
||||||
|
app.use((req: any, _res: any, next: any) => {
|
||||||
|
req.actor = { type: "board" };
|
||||||
|
next();
|
||||||
|
});
|
||||||
|
|
||||||
|
app.use(voiceRoutes());
|
||||||
|
return app;
|
||||||
|
}
|
||||||
|
|
||||||
|
describe("POST /transcribe", () => {
|
||||||
|
beforeEach(() => {
|
||||||
|
vi.clearAllMocks();
|
||||||
|
});
|
||||||
|
|
||||||
|
it("returns 200 with { text, language } for valid audio upload", async () => {
|
||||||
|
const app = buildApp();
|
||||||
|
const fakeAudio = Buffer.from("fake-audio-bytes");
|
||||||
|
|
||||||
|
const res = await supertest(app)
|
||||||
|
.post("/transcribe")
|
||||||
|
.attach("audio", fakeAudio, { filename: "audio.webm", contentType: "audio/webm" });
|
||||||
|
|
||||||
|
expect(res.status).toBe(200);
|
||||||
|
expect(res.body).toHaveProperty("text");
|
||||||
|
expect(res.body.text).toBe("Hello world");
|
||||||
|
});
|
||||||
|
|
||||||
|
it("returns 400 when audio field is missing", async () => {
|
||||||
|
const app = buildApp();
|
||||||
|
|
||||||
|
const res = await supertest(app)
|
||||||
|
.post("/transcribe")
|
||||||
|
.send({});
|
||||||
|
|
||||||
|
expect(res.status).toBe(400);
|
||||||
|
expect(res.body).toEqual({ error: "Missing audio field" });
|
||||||
|
});
|
||||||
|
});
|
||||||
|
|
||||||
|
describe("POST /synthesize", () => {
|
||||||
|
beforeEach(() => {
|
||||||
|
vi.clearAllMocks();
|
||||||
|
});
|
||||||
|
|
||||||
|
it("returns 200 with audio/wav content-type for valid text", async () => {
|
||||||
|
const app = buildApp();
|
||||||
|
|
||||||
|
const res = await supertest(app)
|
||||||
|
.post("/synthesize")
|
||||||
|
.send({ text: "Hello" });
|
||||||
|
|
||||||
|
expect(res.status).toBe(200);
|
||||||
|
expect(res.headers["content-type"]).toMatch(/audio\/wav/);
|
||||||
|
});
|
||||||
|
|
||||||
|
it("returns 400 when text is missing", async () => {
|
||||||
|
const app = buildApp();
|
||||||
|
|
||||||
|
const res = await supertest(app)
|
||||||
|
.post("/synthesize")
|
||||||
|
.send({});
|
||||||
|
|
||||||
|
expect(res.status).toBe(400);
|
||||||
|
expect(res.body).toEqual({ error: "text is required" });
|
||||||
|
});
|
||||||
|
|
||||||
|
it("returns 400 when text is not a string", async () => {
|
||||||
|
const app = buildApp();
|
||||||
|
|
||||||
|
const res = await supertest(app)
|
||||||
|
.post("/synthesize")
|
||||||
|
.send({ text: 42 });
|
||||||
|
|
||||||
|
expect(res.status).toBe(400);
|
||||||
|
expect(res.body).toEqual({ error: "text is required" });
|
||||||
|
});
|
||||||
|
});
|
||||||
47
server/src/routes/voice.ts
Normal file
47
server/src/routes/voice.ts
Normal file
|
|
@ -0,0 +1,47 @@
|
||||||
|
import { Router } from "express";
|
||||||
|
import multer from "multer";
|
||||||
|
import { assertBoard } from "./authz.js";
|
||||||
|
import { voicePipelineService } from "../services/voice-pipeline.js";
|
||||||
|
import { MAX_ATTACHMENT_BYTES } from "../attachment-types.js";
|
||||||
|
|
||||||
|
export function voiceRoutes(): Router {
|
||||||
|
const router = Router();
|
||||||
|
const svc = voicePipelineService();
|
||||||
|
const audioUpload = multer({
|
||||||
|
storage: multer.memoryStorage(),
|
||||||
|
limits: { fileSize: MAX_ATTACHMENT_BYTES, files: 1 },
|
||||||
|
});
|
||||||
|
|
||||||
|
// POST /api/transcribe — transcribe uploaded audio via VoicePipelineService
|
||||||
|
router.post("/transcribe", async (req, res) => {
|
||||||
|
assertBoard(req);
|
||||||
|
await new Promise<void>((resolve, reject) =>
|
||||||
|
audioUpload.single("audio")(req, res, (err) => (err ? reject(err) : resolve()))
|
||||||
|
);
|
||||||
|
const file = (req as any).file as { buffer: Buffer; mimetype: string } | undefined;
|
||||||
|
if (!file) {
|
||||||
|
res.status(400).json({ error: "Missing audio field" });
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
const fmt = file.mimetype.includes("ogg") ? "ogg"
|
||||||
|
: file.mimetype.includes("wav") ? "wav"
|
||||||
|
: "webm";
|
||||||
|
const result = await svc.transcribe(file.buffer, fmt);
|
||||||
|
res.json(result);
|
||||||
|
});
|
||||||
|
|
||||||
|
// POST /api/synthesize — synthesize text to speech via VoicePipelineService
|
||||||
|
router.post("/synthesize", async (req, res) => {
|
||||||
|
assertBoard(req);
|
||||||
|
const { text, voiceId } = req.body as { text?: string; voiceId?: string };
|
||||||
|
if (!text || typeof text !== "string") {
|
||||||
|
res.status(400).json({ error: "text is required" });
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
const audioBuffer = await svc.synthesize(text, voiceId);
|
||||||
|
res.setHeader("Content-Type", "audio/wav");
|
||||||
|
res.send(audioBuffer);
|
||||||
|
});
|
||||||
|
|
||||||
|
return router;
|
||||||
|
}
|
||||||
Loading…
Add table
Reference in a new issue