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]>
2026-10-19 21:21:04 +01:00
parent 727cbf53c8
commit 163d9a434c
37 changed files with 936 additions and 197 deletions
@@ -0,0 +1,37 @@
+import fetchApi from "@moduletrace/twui/utils/fetch/fetchApi";
+import fileInputToBase64 from "@moduletrace/twui/utils/form/fileInputToBase64";
+import type { APIResponseObject } from "@moduletrace/bunext/types";
+import type { TranscribeVoiceRequest } from "@/src/schemas/bot-schema";
+
+type Params = {
+    bot_id: number;
+    workspace_id?: number | null;
+    audio: Blob;
+};
+
+/**
+ * Sends a composer dictation to be turned into text with the bot's
+ * transcription model.
+ */
+export default async function transcribeVoice({
+    bot_id,
+    workspace_id,
+    audio,
+}: Params): Promise<APIResponseObject<{ text: string }>> {
+    const ext = audio.type.split("/").pop() || "webm";
+    const { fileBase64Full } = await fileInputToBase64({
+        inputFile: new File([audio], `dictation.${ext}`, { type: audio.type }),
+    });
+
+    if (!fileBase64Full) {
+        return { success: false, msg: `Couldn't read the recording.` };
+    }
+
+    return await fetchApi<
+        TranscribeVoiceRequest,
+        APIResponseObject<{ text: string }>
+    >(`/api/admin/bots/transcribe`, {
+        method: "POST",
+        body: { bot_id, workspace_id, data_url: fileBase64Full },
+    });
+}