Add dictation and streamed read-aloud to the chat

- A mic in the composer records, transcribes with the bot's
  transcription model (api/admin/bots/transcribe) and writes the text
  into the input at the cursor to edit before sending. Escape cancels;
  recordings aren't stored.
- Every bot message has a read-aloud button that plays
  GET api/admin/bots/speak-message, streamed from the provider as the
  audio is made, so it starts in a couple of seconds. One message plays
  at a time; only the user's own sessions can be read.
- Both buttons stay visible but disabled while the bot has no model for
  them (bot_voice page prop).
- Transcription and speech no longer pick free models automatically:
  they're not available until a model is picked, and Settings says so.
  Transcription lists speech-to-text models only, so the chat-model
  transcript path and its missing-audio check are gone.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

src/harness/catalog/model-serves-harness.test.ts

@@ -30,7 +30,7 @@ describe("modelServesHarness", () => {
         ).toBe(true);
     });
 
-    test("transcription takes speech-to-text or audio-hearing chat models", () => {
+    test("transcription takes speech-to-text models only", () => {
         expect(
             modelServesHarness({
                 model: {
@@ -46,7 +46,7 @@ describe("modelServesHarness", () => {
                 model: { ...chat, input_modalities: ["text", "audio"] },
                 harness: "transcription",
             }),
-        ).toBe(true);
+        ).toBe(false);
         expect(
             modelServesHarness({ model: chat, harness: "transcription" }),
         ).toBe(false);

src/harness/catalog/model-serves-harness.ts

@@ -13,7 +13,8 @@ type Params = {
  * Whether a model can do a harness's job:
  * - text: reads and writes text, and calls tools (bots work through tools)
  * - vision: reads images, writes text
- * - transcription: a speech-to-text model, or a chat model that hears audio
+ * - transcription: a speech-to-text model (never a chat model that hears
+ *   audio: free ones often drop it)
  * - speech: a text-to-speech model
  * - image: makes images
  */
@@ -31,10 +32,7 @@ export default function modelServesHarness({ model, harness }: Params) {
             return input.has("image") && output.has("text");
 
         case "transcription":
-            return (
-                output.has("transcription") ||
-                (input.has("audio") && output.has("text"))
-            );
+            return output.has("transcription");
 
         case "speech":
             return output.has("speech");

src/harness/catalog/rank-auto-models.test.ts

@@ -106,28 +106,24 @@ describe("rankAutoModels", () => {
             "google/gemma-4-31b-it:free",
             "openrouter/free",
         ]);
-        expect(
-            slugs(rankAutoModels({ models: live, harness: "transcription" })),
-        ).toEqual(["thinkingmachines/inkling-small:free"]);
-        expect(rankAutoModels({ models: live, harness: "speech" })).toEqual(
-            [],
-        );
     });
 
-    test("puts speech-to-text models ahead of chat models that hear audio", () => {
-        const ranked = rankAutoModels({
-            models: [
-                model("deepseek/omni", { input_modalities: ["text", "audio"] }),
-                model("acme/scribe", {
-                    input_modalities: ["audio"],
-                    output_modalities: ["transcription"],
-                    supports_tools: false,
-                }),
-            ],
-            harness: "transcription",
-        });
+    test("never picks for transcription or speech", () => {
+        const models = [
+            model("deepseek/omni", { input_modalities: ["text", "audio"] }),
+            model("acme/scribe", {
+                input_modalities: ["audio"],
+                output_modalities: ["transcription"],
+                supports_tools: false,
+            }),
+            model("acme/voice", {
+                output_modalities: ["speech"],
+                supports_tools: false,
+            }),
+        ];
 
-        expect(slugs(ranked)).toEqual(["acme/scribe", "deepseek/omni"]);
+        expect(rankAutoModels({ models, harness: "transcription" })).toEqual([]);
+        expect(rankAutoModels({ models, harness: "speech" })).toEqual([]);
     });
 
     test("drops retired and unscored small models from other vendors", () => {

src/harness/catalog/rank-auto-models.ts

@@ -2,6 +2,7 @@ import { AppData } from "@/src/data/app-data";
 import {
     AutoModelRouterSlugs,
     AutoModelVendorPreference,
+    Harnesses,
     SmallModelPattern,
     SpecialistModelPattern,
     type HarnessKind,
@@ -26,13 +27,16 @@ type Params<T extends HarnessCatalogModel> = {
  * 3. routers such as `openrouter/free`, last
  *
  * Within a group, benchmarked models come first by intelligence index,
- * then the rest: full-size before small variants, newest first.
+ * then the rest: full-size before small variants, newest first. None for
+ * a harness that isn't `automatic` (transcription, speech).
  */
 export default function rankAutoModels<T extends HarnessCatalogModel>({
     models,
     harness,
     now = Date.now(),
 }: Params<T>): T[] {
+    if (!Harnesses.find((h) => h.value == harness)?.automatic) return [];
+
     const ranked = models
         .filter(
             (model) =>
@@ -50,23 +54,12 @@ export default function rankAutoModels<T extends HarnessCatalogModel>({
     return ranked
         .sort(
             (a, b) =>
-                (harness == "transcription"
-                    ? Number(!isSpeechToText(a.model)) -
-                      Number(!isSpeechToText(b.model))
-                    : 0) ||
                 a.tier - b.tier ||
                 compareInTier(a.model, b.model),
         )
         .map((entry) => entry.model);
 }
 
-/**
- * Dedicated speech-to-text models transcribe before chat models that hear
- * audio: some free chat endpoints list audio input but drop it.
- */
-function isSpeechToText(model: HarnessCatalogModel) {
-    return model.output_modalities.includes("transcription");
-}
 
 const OtherTier = AutoModelVendorPreference.length;
 const RouterTier = OtherTier + 1;