feat: whisper support

src/lib/apis/audio/index.ts

@@ -0,0 +1,31 @@
+import { AUDIO_API_BASE_URL } from '$lib/constants';
+
+export const transcribeAudio = async (token: string, file: File) => {
+	const data = new FormData();
+	data.append('file', file);
+
+	let error = null;
+	const res = await fetch(`${AUDIO_API_BASE_URL}/transcribe`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			authorization: `Bearer ${token}`
+		},
+		body: data
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};

src/lib/components/chat/MessageInput.svelte

@@ -11,6 +11,7 @@
 	import { SUPPORTED_FILE_TYPE, SUPPORTED_FILE_EXTENSIONS } from '$lib/constants';
 	import Documents from './MessageInput/Documents.svelte';
 	import Models from './MessageInput/Models.svelte';
+	import { transcribeAudio } from '$lib/apis/audio';
 
 	export let submitPrompt: Function;
 	export let stopResponse: Function;
@@ -201,6 +202,9 @@
 					console.log(file, file.name.split('.').at(-1));
 					if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
 						reader.readAsDataURL(file);
+					} else if (['audio/mpeg', 'audio/wav'].includes(file['type'])) {
+						const res = await transcribeAudio(localStorage.token, file);
+						console.log(res);
 					} else if (
 						SUPPORTED_FILE_TYPE.includes(file['type']) ||
 						SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))

src/lib/constants.ts

@@ -7,6 +7,7 @@ export const WEBUI_API_BASE_URL = `${WEBUI_BASE_URL}/api/v1`;
 export const OLLAMA_API_BASE_URL = `${WEBUI_BASE_URL}/ollama/api`;
 export const OPENAI_API_BASE_URL = `${WEBUI_BASE_URL}/openai/api`;
 export const RAG_API_BASE_URL = `${WEBUI_BASE_URL}/rag/api/v1`;
+export const AUDIO_API_BASE_URL = `${WEBUI_BASE_URL}/audio/api/v1`;
 
 export const WEB_UI_VERSION = 'v1.0.0-alpha-static';