fix: update realtime model names to match OpenAI GA release

Transcription: gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1.
Translation: gpt-4o-transcribe, gpt-4o-mini-transcribe.
Removed fake models: gpt-realtime-translate, gpt-realtime-whisper.
Added dated snapshots to canary known-models set.

Author: jpr5

DRIFT.md

@@ -131,7 +131,7 @@ Uses `describe.skipIf(!GOOGLE_API_KEY)` like other Gemini tests. The Interaction
 
 **GA Realtime Drift Tests**:
 
-- **Model canary** — Verifies all 5 GA models exist (`gpt-realtime-2`, `gpt-realtime-1.5`, `gpt-realtime-mini`, `gpt-realtime-translate`, `gpt-realtime-whisper`) and flags unknown realtime models
+- **Model canary** — Verifies GA models exist (`gpt-realtime`, `gpt-realtime-2`, `gpt-realtime-1.5`, `gpt-realtime-mini` and dated snapshots) and flags unknown realtime models
 - **Protocol probe** — Connects with both GA and Beta protocol, normalizes event sequences, and verifies consistency
 - **Event shape validation** — GA event names (`response.output_text.delta`, `conversation.item.added`, `conversation.item.done`) and nested session config (`session.audio.*`, `session.type`, `session.reasoning`)
 

README.md

@@ -57,7 +57,7 @@ Run them all on one port with `npx @copilotkit/aimock --config aimock.json`, or
 - **Per-Request Strict Mode** — `X-AIMock-Strict` header overrides the server-level `--strict` flag per request (`true`/`1` = strict, `false`/`0` = lenient)
 - **[Drift Detection](https://aimock.copilotkit.dev/drift-detection)** — Daily CI validation against real APIs
 - **[Streaming Physics](https://aimock.copilotkit.dev/streaming-physics)** — Configurable `ttft`, `tps`, and `jitter`
-- **[WebSocket APIs](https://aimock.copilotkit.dev/websocket)** — OpenAI Realtime (GA protocol with 5 models: gpt-realtime-2, gpt-realtime-1.5, gpt-realtime-mini, gpt-realtime-translate, gpt-realtime-whisper; transcription/translation session types; image input; commentary phase), Responses WS, Gemini Live
+- **[WebSocket APIs](https://aimock.copilotkit.dev/websocket)** — OpenAI Realtime (GA protocol with models: gpt-realtime, gpt-realtime-2, gpt-realtime-1.5, gpt-realtime-mini; transcription/translation via gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1; image input; commentary phase), Responses WS, Gemini Live
 - **[Prometheus Metrics](https://aimock.copilotkit.dev/metrics)** — Request counts, latencies, fixture match rates
 - **[Docker + Helm](https://aimock.copilotkit.dev/docker)** — Container image and Helm chart for CI/CD
 - **[Vitest & Jest Plugins](https://aimock.copilotkit.dev/test-plugins)** — Zero-config `useAimock()` with auto lifecycle and env patching

docs/websocket/index.html

@@ -130,6 +130,11 @@ <h3>Supported Models</h3>
             </tr>
           </thead>
           <tbody>
+            <tr>
+              <td>gpt-realtime</td>
+              <td>conversation</td>
+              <td>Base alias &mdash; resolves to latest GA model</td>
+            </tr>
             <tr>
               <td>gpt-realtime-2</td>
               <td>conversation</td>
@@ -146,14 +151,19 @@ <h3>Supported Models</h3>
               <td>Smaller, faster GA model</td>
             </tr>
             <tr>
-              <td>gpt-realtime-translate</td>
-              <td>translation</td>
-              <td>Real-time speech translation</td>
+              <td>gpt-4o-transcribe</td>
+              <td>transcription, translation</td>
+              <td>Speech transcription and translation</td>
+            </tr>
+            <tr>
+              <td>gpt-4o-mini-transcribe</td>
+              <td>transcription, translation</td>
+              <td>Smaller transcription and translation model</td>
             </tr>
             <tr>
-              <td>gpt-realtime-whisper</td>
+              <td>whisper-1</td>
               <td>transcription</td>
-              <td>Real-time speech transcription</td>
+              <td>Legacy Whisper transcription model</td>
             </tr>
           </tbody>
         </table>
@@ -166,11 +176,12 @@ <h3>Session Types</h3>
           </li>
           <li>
             <strong>transcription</strong> &mdash; Audio-to-text transcription (requires
-            <code>gpt-realtime-whisper</code>)
+            <code>gpt-4o-transcribe</code>, <code>gpt-4o-mini-transcribe</code>, or
+            <code>whisper-1</code>)
           </li>
           <li>
             <strong>translation</strong> &mdash; Real-time speech translation (requires
-            <code>gpt-realtime-translate</code>)
+            <code>gpt-4o-transcribe</code> or <code>gpt-4o-mini-transcribe</code>)
           </li>
         </ul>
 

scripts/update-competitive-matrix.ts

@@ -90,10 +90,11 @@ const FEATURE_RULES: FeatureRule[] = [
     ],
   },
   {
-    rowLabel: "Realtime translate/whisper",
+    rowLabel: "Realtime transcription/translation",
     keywords: [
-      "gpt-realtime-translate",
-      "gpt-realtime-whisper",
+      "gpt-4o-transcribe",
+      "gpt-4o-mini-transcribe",
+      "whisper-1",
       "realtime.*transcription",
       "realtime.*translation",
     ],

src/__tests__/competitive-matrix.test.ts

@@ -101,10 +101,11 @@ const FEATURE_RULES: FeatureRule[] = [
     ],
   },
   {
-    rowLabel: "Realtime translate/whisper",
+    rowLabel: "Realtime transcription/translation",
     keywords: [
-      "gpt-realtime-translate",
-      "gpt-realtime-whisper",
+      "gpt-4o-transcribe",
+      "gpt-4o-mini-transcribe",
+      "whisper-1",
       "realtime.*transcription",
       "realtime.*translation",
     ],

src/__tests__/drift/ws-realtime.drift.ts

@@ -56,18 +56,27 @@ describe.skipIf(!OPENAI_API_KEY)("OpenAI Realtime API drift", () => {
     const models = await listOpenAIModels(config.apiKey);
 
     const gaModels = [
+      "gpt-realtime",
       "gpt-realtime-2",
+      "gpt-realtime-2025-08-28",
       "gpt-realtime-1.5",
       "gpt-realtime-mini",
-      "gpt-realtime-translate",
-      "gpt-realtime-whisper",
+      "gpt-realtime-mini-2025-10-06",
+      "gpt-realtime-mini-2025-12-15",
     ];
     const knownModels = new Set([
       ...gaModels,
+      // Audio models also valid in realtime sessions
+      "gpt-audio-1.5",
+      "gpt-audio-mini",
+      "gpt-audio-mini-2025-10-06",
+      "gpt-audio-mini-2025-12-15",
       // Legacy preview models (may still appear)
       "gpt-4o-realtime-preview",
       "gpt-4o-mini-realtime-preview",
       "gpt-4o-realtime-preview-2024-10-01",
+      "gpt-4o-realtime-preview-2024-12-17",
+      "gpt-4o-realtime-preview-2025-06-03",
       "gpt-4o-mini-realtime-preview-2024-12-17",
     ]);
 

src/__tests__/ws-realtime.test.ts

@@ -1295,14 +1295,14 @@ describe("WebSocket /v1/realtime", () => {
     // Skip session.created
     await ws.waitForMessages(1);
 
-    // Update session to transcription mode with whisper model
-    ws.send(sessionUpdate({ type: "transcription", model: "gpt-realtime-whisper" }));
+    // Update session to transcription mode with transcribe model
+    ws.send(sessionUpdate({ type: "transcription", model: "gpt-4o-transcribe" }));
 
     const updateRaw = await ws.waitForMessages(2);
     const updateEvent = parseEvents(updateRaw.slice(1))[0];
     expect(updateEvent.type).toBe("session.updated");
     expect((updateEvent.session as Record<string, unknown>).type).toBe("transcription");
-    expect((updateEvent.session as Record<string, unknown>).model).toBe("gpt-realtime-whisper");
+    expect((updateEvent.session as Record<string, unknown>).model).toBe("gpt-4o-transcribe");
 
     // Send audio buffer messages
     ws.send(JSON.stringify({ type: "input_audio_buffer.append", audio: "base64data" }));
@@ -1389,13 +1389,13 @@ describe("WebSocket /v1/realtime", () => {
 
     await ws.waitForMessages(1); // session.created
 
-    ws.send(sessionUpdate({ type: "translation", model: "gpt-realtime-translate" }));
+    ws.send(sessionUpdate({ type: "translation", model: "gpt-4o-transcribe" }));
 
     const raw = await ws.waitForMessages(2);
     const event = parseEvents(raw.slice(1))[0];
     expect(event.type).toBe("session.updated");
     expect((event.session as Record<string, unknown>).type).toBe("translation");
-    expect((event.session as Record<string, unknown>).model).toBe("gpt-realtime-translate");
+    expect((event.session as Record<string, unknown>).model).toBe("gpt-4o-transcribe");
 
     ws.close();
   });
@@ -1425,7 +1425,7 @@ describe("WebSocket /v1/realtime", () => {
 
     await ws.waitForMessages(1); // session.created
 
-    ws.send(sessionUpdate({ type: "translation", model: "gpt-realtime-2" }));
+    ws.send(sessionUpdate({ type: "translation", model: "gpt-realtime-mini" }));
 
     const raw = await ws.waitForMessages(2);
     const event = parseEvents(raw.slice(1))[0];
@@ -1444,7 +1444,7 @@ describe("WebSocket /v1/realtime", () => {
 
     await ws.waitForMessages(1); // session.created
 
-    ws.send(sessionUpdate({ type: "translation", model: "gpt-realtime-translate" }));
+    ws.send(sessionUpdate({ type: "translation", model: "gpt-4o-transcribe" }));
     await ws.waitForMessages(2); // session.updated
 
     ws.send(JSON.stringify({ type: "input_audio_buffer.commit" }));
@@ -1539,11 +1539,13 @@ describe("WebSocket /v1/realtime", () => {
 
   // ── GA model acceptance tests ───────────────────────────────────────────
   it.each([
+    "gpt-realtime",
     "gpt-realtime-2",
+    "gpt-realtime-2025-08-28",
     "gpt-realtime-1.5",
     "gpt-realtime-mini",
-    "gpt-realtime-translate",
-    "gpt-realtime-whisper",
+    "gpt-realtime-mini-2025-10-06",
+    "gpt-realtime-mini-2025-12-15",
   ])("accepts GA model %s via query parameter", async (model) => {
     instance = await createServer(allFixtures);
     const ws = await connectWebSocket(instance.url, `/v1/realtime?model=${model}`);
@@ -1598,7 +1600,7 @@ describe("WebSocket /v1/realtime", () => {
 
   it("sets _endpointType to realtime-transcription for transcription sessions", async () => {
     instance = await createServer(allFixtures);
-    const ws = await connectWebSocket(instance.url, "/v1/realtime?model=gpt-realtime-whisper");
+    const ws = await connectWebSocket(instance.url, "/v1/realtime?model=gpt-4o-transcribe");
 
     await ws.waitForMessages(1); // session.created
 
@@ -1624,7 +1626,7 @@ describe("WebSocket /v1/realtime", () => {
 
   it("sets _endpointType to realtime-translation for translation sessions", async () => {
     instance = await createServer(allFixtures);
-    const ws = await connectWebSocket(instance.url, "/v1/realtime?model=gpt-realtime-translate");
+    const ws = await connectWebSocket(instance.url, "/v1/realtime?model=gpt-4o-transcribe");
 
     await ws.waitForMessages(1); // session.created
 

src/ws-realtime.ts

@@ -485,8 +485,12 @@ async function processMessage(
         } | null;
 
       // Validate model+type combinations (rollback on failure)
-      const transcriptionModels = new Set(["gpt-realtime-whisper"]);
-      const translationModels = new Set(["gpt-realtime-translate"]);
+      const transcriptionModels = new Set([
+        "gpt-4o-transcribe",
+        "gpt-4o-mini-transcribe",
+        "whisper-1",
+      ]);
+      const translationModels = new Set(["gpt-4o-transcribe", "gpt-4o-mini-transcribe"]);
 
       if (session.type === "transcription" && !transcriptionModels.has(session.model)) {
         session.model = prevModel;