tbenandClaude Opus 5.5
163d9a434c
- 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]>
70 lines
2.4 KiB
TypeScript
70 lines
2.4 KiB
TypeScript
import userAuth from "@/src/functions/backend/auth/user-auth";
|
|
import grabSpeakableMessage from "@/src/functions/backend/db/bots/grab-speakable-message";
|
|
import speakText from "@/src/harness/audio/speak-text";
|
|
import HarnessError from "@/src/harness/harness-error";
|
|
import { SpeakBotMessageRequestSchema } from "@/src/schemas/bot-schema";
|
|
import AppError from "@/src/utils/app-error";
|
|
import parseWithSchema from "@/src/utils/parse-with-schema";
|
|
import safeErrorMessage from "@/src/utils/safe-error-message";
|
|
import speechText from "@/src/utils/speech-text";
|
|
import type {
|
|
APIResponseObject,
|
|
BunextAPIRouteHandler,
|
|
} from "@moduletrace/bunext/types";
|
|
|
|
/**
|
|
* `GET ?message_id=`: reads one of the bot's messages in the user's own
|
|
* conversation aloud with the bot's speech model and voice, streamed as
|
|
* the provider makes it, so an `<audio>` pointed here starts playing
|
|
* within a couple of seconds. Closing the player stops the provider call.
|
|
* Nothing is stored; the browser may keep it for an hour.
|
|
*/
|
|
export const handler: BunextAPIRouteHandler<APIResponseObject> = async ({ req, query }) => {
|
|
try {
|
|
if (req.method != "GET") {
|
|
throw new AppError(`Method not allowed`);
|
|
}
|
|
|
|
const { user } = await userAuth({ req });
|
|
|
|
if (!user?.logged_in_status || !user.id) {
|
|
return { success: false, msg: `Unauthorized`, logoutUser: true };
|
|
}
|
|
|
|
const { message_id } = parseWithSchema({
|
|
schema: SpeakBotMessageRequestSchema,
|
|
data: query,
|
|
});
|
|
|
|
const { message, conversation } = await grabSpeakableMessage({
|
|
user_id: Number(user.id),
|
|
message_id,
|
|
});
|
|
|
|
const text = speechText({ text: message.text || "" });
|
|
|
|
if (!text) {
|
|
throw new AppError(`There's nothing to read in that message.`);
|
|
}
|
|
|
|
const audio = await speakText({
|
|
text,
|
|
bot_id: conversation.bot.id,
|
|
workspace_id: conversation.workspace_id,
|
|
signal: req.signal,
|
|
});
|
|
|
|
return new Response(audio.stream, {
|
|
headers: {
|
|
"Content-Type": audio.media_type,
|
|
"Cache-Control": "private, max-age=3600",
|
|
},
|
|
});
|
|
} catch (error: unknown) {
|
|
return {
|
|
success: false,
|
|
msg: error instanceof HarnessError ? error.message : safeErrorMessage({ error }),
|
|
};
|
|
}
|
|
};
|