open-webui/src/lib/components/chat/Settings/Audio.svelte

<script lang="ts">
	import { toast } from 'svelte-sonner';
	import { createEventDispatcher, onMount, getContext } from 'svelte';

	import { user, settings, config } from '$lib/stores';
	import { getVoices as _getVoices } from '$lib/apis/audio';

	import Switch from '$lib/components/common/Switch.svelte';
	const dispatch = createEventDispatcher();

	const i18n = getContext('i18n');

	export let saveSettings: Function;

	// Audio
	let conversationMode = false;
	let speechAutoSend = false;
	let responseAutoPlayback = false;
	let nonLocalVoices = false;

	let STTEngine = '';

	let voices = [];
	let voice = '';

	// Audio speed control
	let playbackRate = 1;
	const speedOptions = [2, 1.75, 1.5, 1.25, 1, 0.75, 0.5];

	const getVoices = async () => {
		if ($config.audio.tts.engine === '') {
			const getVoicesLoop = setInterval(async () => {
				voices = await speechSynthesis.getVoices();

				// do your loop
				if (voices.length > 0) {
					clearInterval(getVoicesLoop);
				}
			}, 100);
		} else {
			const res = await _getVoices(localStorage.token).catch((e) => {
				toast.error(e);
			});

			if (res) {
				console.log(res);
				voices = res.voices;
			}
		}
	};

	const toggleResponseAutoPlayback = async () => {
		responseAutoPlayback = !responseAutoPlayback;
		saveSettings({ responseAutoPlayback: responseAutoPlayback });
	};

	const toggleSpeechAutoSend = async () => {
		speechAutoSend = !speechAutoSend;
		saveSettings({ speechAutoSend: speechAutoSend });
	};

	onMount(async () => {
		playbackRate = $settings.audio?.tts?.playbackRate ?? 1;
		conversationMode = $settings.conversationMode ?? false;
		speechAutoSend = $settings.speechAutoSend ?? false;
		responseAutoPlayback = $settings.responseAutoPlayback ?? false;

		STTEngine = $settings?.audio?.stt?.engine ?? '';

		if ($settings?.audio?.tts?.defaultVoice === $config.audio.tts.voice) {
			voice = $settings?.audio?.tts?.voice ?? $config.audio.tts.voice ?? '';
		} else {
			voice = $config.audio.tts.voice ?? '';
		}

		nonLocalVoices = $settings.audio?.tts?.nonLocalVoices ?? false;

		await getVoices();
	});
</script>

<form
	class="flex flex-col h-full justify-between space-y-3 text-sm"
	on:submit|preventDefault={async () => {
		saveSettings({
			audio: {
				stt: {
					engine: STTEngine !== '' ? STTEngine : undefined
				},
				tts: {
					playbackRate: playbackRate,
					voice: voice !== '' ? voice : undefined,
					defaultVoice: $config?.audio?.tts?.voice ?? '',
					nonLocalVoices: $config.audio.tts.engine === '' ? nonLocalVoices : undefined
				}
			}
		});
		dispatch('save');
	}}
>
	<div class=" space-y-3 pr-1.5 overflow-y-scroll">
		<div>
			<div class=" mb-1 text-sm font-medium">{$i18n.t('STT Settings')}</div>

			{#if $config.audio.stt.engine !== 'web'}
				<div class=" py-0.5 flex w-full justify-between">
					<div class=" self-center text-xs font-medium">{$i18n.t('Speech-to-Text Engine')}</div>
					<div class="flex items-center relative">
						<select
							class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
							bind:value={STTEngine}
							placeholder="Select an engine"
						>
							<option value="">{$i18n.t('Default')}</option>
							<option value="web">{$i18n.t('Web API')}</option>
						</select>
					</div>
				</div>
			{/if}

			<div class=" py-0.5 flex w-full justify-between">
				<div class=" self-center text-xs font-medium">
					{$i18n.t('Instant Auto-Send After Voice Transcription')}
				</div>

				<button
					class="p-1 px-3 text-xs flex rounded transition"
					on:click={() => {
						toggleSpeechAutoSend();
					}}
					type="button"
				>
					{#if speechAutoSend === true}
						<span class="ml-2 self-center">{$i18n.t('On')}</span>
					{:else}
						<span class="ml-2 self-center">{$i18n.t('Off')}</span>
					{/if}
				</button>
			</div>
		</div>

		<div>
			<div class=" mb-1 text-sm font-medium">{$i18n.t('TTS Settings')}</div>

			<div class=" py-0.5 flex w-full justify-between">
				<div class=" self-center text-xs font-medium">{$i18n.t('Auto-playback response')}</div>

				<button
					class="p-1 px-3 text-xs flex rounded transition"
					on:click={() => {
						toggleResponseAutoPlayback();
					}}
					type="button"
				>
					{#if responseAutoPlayback === true}
						<span class="ml-2 self-center">{$i18n.t('On')}</span>
					{:else}
						<span class="ml-2 self-center">{$i18n.t('Off')}</span>
					{/if}
				</button>
			</div>

			<div class=" py-0.5 flex w-full justify-between">
				<div class=" self-center text-xs font-medium">{$i18n.t('Speech Playback Speed')}</div>

				<div class="flex items-center relative">
					<select
						class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
						bind:value={playbackRate}
					>
						{#each speedOptions as option}
							<option value={option} selected={playbackRate === option}>{option}x</option>
						{/each}
					</select>
				</div>
			</div>
		</div>

		<hr class=" dark:border-gray-850" />

		{#if $config.audio.tts.engine === ''}
			<div>
				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Voice')}</div>
				<div class="flex w-full">
					<div class="flex-1">
						<select
							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
							bind:value={voice}
						>
							<option value="" selected={voice !== ''}>{$i18n.t('Default')}</option>
							{#each voices.filter((v) => nonLocalVoices || v.localService === true) as _voice}
								<option
									value={_voice.name}
									class="bg-gray-100 dark:bg-gray-700"
									selected={voice === _voice.name}>{_voice.name}</option
								>
							{/each}
						</select>
					</div>
				</div>
				<div class="flex items-center justify-between my-1.5">
					<div class="text-xs">
						{$i18n.t('Allow non-local voices')}
					</div>

					<div class="mt-1">
						<Switch bind:state={nonLocalVoices} />
					</div>
				</div>
			</div>
		{:else if $config.audio.tts.engine !== ''}
			<div>
				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Voice')}</div>
				<div class="flex w-full">
					<div class="flex-1">
						<input
							list="voice-list"
							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
							bind:value={voice}
							placeholder="Select a voice"
						/>

						<datalist id="voice-list">
							{#each voices as voice}
								<option value={voice.id}>{voice.name}</option>
							{/each}
						</datalist>
					</div>
				</div>
			</div>
		{/if}
	</div>

	<div class="flex justify-end text-sm font-medium">
		<button
			class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full"
			type="submit"
		>
			{$i18n.t('Save')}
		</button>
	</div>
</form>