feat: support openai tts

This commit is contained in:
Hk-Gosuto
2024-03-03 15:15:23 +08:00
parent d2733a9128
commit c3656609ab
17 changed files with 475 additions and 20 deletions

View File

@@ -14,6 +14,8 @@ import RenameIcon from "../icons/rename.svg";
import ExportIcon from "../icons/share.svg";
import ReturnIcon from "../icons/return.svg";
import CopyIcon from "../icons/copy.svg";
import SpeakIcon from "../icons/speak.svg";
import SpeakStopIcon from "../icons/speak-stop.svg";
import LoadingIcon from "../icons/three-dots.svg";
import PromptIcon from "../icons/prompt.svg";
import MaskIcon from "../icons/mask.svg";
@@ -83,6 +85,7 @@ import {
CHAT_PAGE_SIZE,
LAST_INPUT_IMAGE_KEY,
LAST_INPUT_KEY,
ModelProvider,
Path,
REQUEST_TIMEOUT_MS,
UNFINISHED_INPUT,
@@ -97,6 +100,9 @@ import { getClientConfig } from "../config/client";
import { useAllModels } from "../utils/hooks";
import Image from "next/image";
import { ClientApi } from "../client/api";
import { createTTSPlayer } from "../utils/audio";
const ttsPlayer = createTTSPlayer();
const Markdown = dynamic(async () => (await import("./markdown")).Markdown, {
loading: () => <LoadingIcon />,
@@ -1008,6 +1014,37 @@ function _Chat() {
});
};
const [speechStatus, setSpeechStatus] = useState(false);
const [speechLoading, setSpeechLoading] = useState(false);
async function openaiSpeech(text: string) {
if (speechStatus) {
ttsPlayer.stop();
setSpeechStatus(false);
} else {
var api: ClientApi;
api = new ClientApi(ModelProvider.GPT);
const config = useAppConfig.getState();
setSpeechLoading(true);
const audioBuffer = await api.llm.speech({
model: config.ttsConfig.model,
input: text,
voice: config.ttsConfig.voice,
speed: config.ttsConfig.speed,
});
setSpeechStatus(true);
ttsPlayer
.play(audioBuffer, () => {
setSpeechStatus(false);
})
.catch((e) => {
console.error("[OpenAI Speech]", e);
showToast(prettyObject(e));
setSpeechStatus(false);
})
.finally(() => setSpeechLoading(false));
}
}
const context: RenderMessage[] = useMemo(() => {
return session.mask.hideContext ? [] : session.mask.context.slice();
}, [session.mask.context, session.mask.hideContext]);
@@ -1361,6 +1398,24 @@ function _Chat() {
icon={<CopyIcon />}
onClick={() => copyToClipboard(message.content)}
/>
{config.ttsConfig.enable && (
<ChatAction
text={
speechStatus
? Locale.Chat.Actions.StopSpeech
: Locale.Chat.Actions.Speech
}
loding={speechLoading}
icon={
speechStatus ? (
<SpeakStopIcon />
) : (
<SpeakIcon />
)
}
onClick={() => openaiSpeech(message.content)}
/>
)}
</>
)}
</div>

View File

@@ -72,6 +72,7 @@ import { nanoid } from "nanoid";
import { PluginConfigList } from "./plugin-config";
import { useMaskStore } from "../store/mask";
import { ProviderType } from "../utils/cloud";
import { TTSConfigList } from "./tts-config";
function EditPromptModal(props: { id: string; onClose: () => void }) {
const promptStore = usePromptStore();
@@ -1198,6 +1199,17 @@ export function Settings() {
/>
</List>
<List>
<TTSConfigList
ttsConfig={config.ttsConfig}
updateConfig={(updater) => {
const ttsConfig = { ...config.ttsConfig };
updater(ttsConfig);
config.update((config) => (config.ttsConfig = ttsConfig));
}}
/>
</List>
<DangerItems />
</div>
</ErrorBoundary>

View File

@@ -0,0 +1,104 @@
import { PluginConfig, TTSConfig, TTSConfigValidator } from "../store";
import Locale from "../locales";
import { ListItem, Select } from "./ui-lib";
import { DEFAULT_TTS_MODELS, DEFAULT_TTS_VOICES } from "../constant";
import { InputRange } from "./input-range";
export function TTSConfigList(props: {
ttsConfig: TTSConfig;
updateConfig: (updater: (config: TTSConfig) => void) => void;
}) {
return (
<>
<ListItem
title={Locale.Settings.TTS.Enable.Title}
subTitle={Locale.Settings.TTS.Enable.SubTitle}
>
<input
type="checkbox"
checked={props.ttsConfig.enable}
onChange={(e) =>
props.updateConfig(
(config) => (config.enable = e.currentTarget.checked),
)
}
></input>
</ListItem>
{/* <ListItem
title={Locale.Settings.TTS.Autoplay.Title}
subTitle={Locale.Settings.TTS.Autoplay.SubTitle}
>
<input
type="checkbox"
checked={props.ttsConfig.autoplay}
onChange={(e) =>
props.updateConfig(
(config) => (config.autoplay = e.currentTarget.checked),
)
}
></input>
</ListItem> */}
<ListItem title={Locale.Settings.TTS.Model}>
<Select
value={props.ttsConfig.model}
onChange={(e) => {
props.updateConfig(
(config) =>
(config.model = TTSConfigValidator.model(
e.currentTarget.value,
)),
);
}}
>
{DEFAULT_TTS_MODELS.map((v, i) => (
<option value={v} key={i}>
{v}
</option>
))}
</Select>
</ListItem>
<ListItem
title={Locale.Settings.TTS.Voice.Title}
subTitle={Locale.Settings.TTS.Voice.SubTitle}
>
<Select
value={props.ttsConfig.voice}
onChange={(e) => {
props.updateConfig(
(config) =>
(config.voice = TTSConfigValidator.voice(
e.currentTarget.value,
)),
);
}}
>
{DEFAULT_TTS_VOICES.map((v, i) => (
<option value={v} key={i}>
{v}
</option>
))}
</Select>
</ListItem>
<ListItem
title={Locale.Settings.TTS.Speed.Title}
subTitle={Locale.Settings.TTS.Speed.SubTitle}
>
<InputRange
value={props.ttsConfig.speed?.toFixed(1)}
min="0.3"
max="4.0"
step="0.1"
onChange={(e) => {
props.updateConfig(
(config) =>
(config.speed = TTSConfigValidator.speed(
e.currentTarget.valueAsNumber,
)),
);
}}
></InputRange>
</ListItem>
</>
);
}

View File

@@ -0,0 +1,119 @@
@import "../styles/animation.scss";
.plugin-page {
height: 100%;
display: flex;
flex-direction: column;
.plugin-page-body {
padding: 20px;
overflow-y: auto;
.plugin-filter {
width: 100%;
max-width: 100%;
margin-bottom: 20px;
animation: slide-in ease 0.3s;
height: 40px;
display: flex;
.search-bar {
flex-grow: 1;
max-width: 100%;
min-width: 0;
outline: none;
}
.search-bar:focus {
border: 1px solid var(--primary);
}
.plugin-filter-lang {
height: 100%;
margin-left: 10px;
}
.plugin-create {
height: 100%;
margin-left: 10px;
box-sizing: border-box;
min-width: 80px;
}
}
.plugin-item {
display: flex;
justify-content: space-between;
padding: 20px;
border: var(--border-in-light);
animation: slide-in ease 0.3s;
&:not(:last-child) {
border-bottom: 0;
}
&:first-child {
border-top-left-radius: 10px;
border-top-right-radius: 10px;
}
&:last-child {
border-bottom-left-radius: 10px;
border-bottom-right-radius: 10px;
}
.plugin-header {
display: flex;
align-items: center;
.plugin-icon {
display: flex;
align-items: center;
justify-content: center;
margin-right: 10px;
}
.plugin-title {
.plugin-name {
font-size: 14px;
font-weight: bold;
}
.plugin-info {
font-size: 12px;
}
.plugin-runtime-warning {
font-size: 12px;
color: #f86c6c;
}
}
}
.plugin-actions {
display: flex;
flex-wrap: nowrap;
transition: all ease 0.3s;
justify-content: center;
align-items: center;
}
@media screen and (max-width: 600px) {
display: flex;
flex-direction: column;
padding-bottom: 10px;
border-radius: 10px;
margin-bottom: 20px;
box-shadow: var(--card-shadow);
&:not(:last-child) {
border-bottom: var(--border-in-light);
}
.plugin-actions {
width: 100%;
justify-content: space-between;
padding-top: 10px;
}
}
}
}
}