OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-06-26 18:26:48 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #5496 from pawel-ochman/azure-tts

Browse Source 
Integrate Azure Speech service for TTS
This commit is contained in:
Timothy Jaeryang Baek
2024-09-19 02:42:45 +02:00
committed by GitHub
parent be44af4680 b4f1a0b5a6
commit 5d3a89dd25
3 changed files with 149 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
src/lib/components/admin/Settings/Audio.svelte
View File

@@ -31,6 +31,8 @@
let TTS_MODEL = '';
let TTS_VOICE = '';
let TTS_SPLIT_ON: TTS_RESPONSE_SPLIT = TTS_RESPONSE_SPLIT.PUNCTUATION;
let TTS_AZURE_SPEECH_REGION = '';
let TTS_AZURE_SPEECH_OUTPUT_FORMAT = '';
let STT_OPENAI_API_BASE_URL = '';
let STT_OPENAI_API_KEY = '';
@@ -87,7 +89,9 @@
ENGINE: TTS_ENGINE,
MODEL: TTS_MODEL,
VOICE: TTS_VOICE,
SPLIT_ON: TTS_SPLIT_ON
SPLIT_ON: TTS_SPLIT_ON,
AZURE_SPEECH_REGION: TTS_AZURE_SPEECH_REGION,
AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT
},
stt: {
OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
@@ -120,6 +124,9 @@
TTS_SPLIT_ON = res.tts.SPLIT_ON || TTS_RESPONSE_SPLIT.PUNCTUATION;
TTS_AZURE_SPEECH_OUTPUT_FORMAT = res.tts.AZURE_SPEECH_OUTPUT_FORMAT;
TTS_AZURE_SPEECH_REGION = res.tts.AZURE_SPEECH_REGION;
STT_OPENAI_API_BASE_URL = res.stt.OPENAI_API_BASE_URL;
STT_OPENAI_API_KEY = res.stt.OPENAI_API_KEY;
@@ -224,6 +231,7 @@
<option value="">{$i18n.t('Web API')}</option>
<option value="openai">{$i18n.t('OpenAI')}</option>
<option value="elevenlabs">{$i18n.t('ElevenLabs')}</option>
<option value="azure">{$i18n.t('Azure AI Speech')}</option>
</select>
</div>
</div>
@@ -252,6 +260,23 @@
/>
</div>
</div>
{:else if TTS_ENGINE === 'azure'}
<div>
<div class="mt-1 flex gap-2 mb-1">
<input
class="flex-1 w-full rounded-lg py-2 pl-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
placeholder={$i18n.t('API Key')}
bind:value={TTS_API_KEY}
required
/>
<input
class="flex-1 w-full rounded-lg py-2 pl-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
placeholder={$i18n.t('Azure Region')}
bind:value={TTS_AZURE_SPEECH_REGION}
required
/>
</div>
</div>
{/if}
<hr class=" dark:border-gray-850 my-2" />
@@ -359,6 +384,49 @@
</div>
</div>
</div>
{:else if TTS_ENGINE === 'azure'}
<div class=" flex gap-2">
<div class="w-full">
<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
<div class="flex w-full">
<div class="flex-1">
<input
list="voice-list"
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
bind:value={TTS_VOICE}
placeholder="Select a voice"
/>
<datalist id="voice-list">
{#each voices as voice}
<option value={voice.id}>{voice.name}</option>
{/each}
</datalist>
</div>
</div>
</div>
<div class="w-full">
<div class=" mb-1.5 text-sm font-medium">
{$i18n.t('Output format')}
<a
href="https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech?tabs=streaming#audio-outputs"
target="_blank"
>
<small>{$i18n.t('Available list')}</small>
</a>
</div>
<div class="flex w-full">
<div class="flex-1">
<input
list="tts-model-list"
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
bind:value={TTS_AZURE_SPEECH_OUTPUT_FORMAT}
placeholder="Select a output format"
/>
</div>
</div>
</div>
</div>
{/if}
<hr class="dark:border-gray-850 my-2" />