Compare commits

..

5 Commits

Author SHA1 Message Date
Dakai
9b4b57748f Merge c3b50a9c93 into 705dffc664 2025-06-11 19:43:09 +08:00
dakai
c3b50a9c93 refactor: optimize playSpeech function in TTSConfigList component 2024-10-27 12:42:16 +08:00
dakai
ab4bf3ba67 remove redundancy code 2024-10-16 11:34:20 +08:00
dakai
67192a7946 follow the rabbit to fix potential issues 2024-10-14 03:46:51 +08:00
dakai
bcd50b89c8 feat: add voice audio preview button in tts-config option 2024-10-14 03:25:44 +08:00
6 changed files with 105 additions and 45 deletions

View File

@@ -22,12 +22,12 @@ English / [简体中文](./README_CN.md)
[![MacOS][MacOS-image]][download-url]
[![Linux][Linux-image]][download-url]
[NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.club) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition)
[NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition)
[saas-url]: https://nextchat.club?utm_source=readme
[saas-image]: https://img.shields.io/badge/NextChat-Saas-green?logo=microsoftedge
[web-url]: https://app.nextchat.club/
[web-url]: https://app.nextchat.dev/
[download-url]: https://github.com/Yidadaa/ChatGPT-Next-Web/releases
[Web-image]: https://img.shields.io/badge/Web-PWA-orange?logo=microsoftedge
[Windows-image]: https://img.shields.io/badge/-Windows-blue?logo=windows

View File

@@ -56,7 +56,7 @@ export interface OpenAIListModelResponse {
export interface RequestPayload {
messages: {
role: "developer" | "system" | "user" | "assistant";
role: "system" | "user" | "assistant";
content: string | MultimodalContent[];
}[];
stream?: boolean;
@@ -238,16 +238,8 @@ export class ChatGPTApi implements LLMApi {
// Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore.
};
// O1 使用 max_completion_tokens 控制token数 (https://platform.openai.com/docs/guides/reasoning#controlling-costs)
if (isO1OrO3) {
// by default the o1/o3 models will not attempt to produce output that includes markdown formatting
// manually add "Formatting re-enabled" developer message to encourage markdown inclusion in model responses
// (https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/reasoning?tabs=python-secure#markdown-output)
requestPayload["messages"].unshift({
role: "developer",
content: "Formatting re-enabled",
});
// o1/o3 uses max_completion_tokens to control the number of tokens (https://platform.openai.com/docs/guides/reasoning#controlling-costs)
requestPayload["max_completion_tokens"] = modelConfig.max_tokens;
}

View File

@@ -1,19 +1,76 @@
import { TTSConfig, TTSConfigValidator } from "../store";
import React, { useState } from "react";
import Locale from "../locales";
import { ListItem, Select } from "./ui-lib";
import {
ModelProvider,
DEFAULT_TTS_ENGINE,
DEFAULT_TTS_ENGINES,
DEFAULT_TTS_MODELS,
DEFAULT_TTS_VOICES,
} from "../constant";
import { InputRange } from "./input-range";
import { IconButton } from "./button";
import SpeakIcon from "../icons/speak.svg";
import SpeakStopIcon from "../icons/speak-stop.svg";
import { createTTSPlayer } from "../utils/audio";
import { useAppConfig } from "../store";
import { ClientApi } from "../client/api";
import { showToast } from "../components/ui-lib";
const ttsPlayer = createTTSPlayer();
export function TTSConfigList(props: {
ttsConfig: TTSConfig;
updateConfig: (updater: (config: TTSConfig) => void) => void;
}) {
const [speechLoading, setSpeechLoading] = useState(false);
const [speechStatus, setSpeechStatus] = useState(false);
const config = useAppConfig.getState();
function stopSpeech() {
ttsPlayer.stop();
setSpeechStatus(false);
}
async function playSpeech(text: string, ttsConfig: TTSConfig) {
try {
const api = new ClientApi(ModelProvider.GPT);
setSpeechLoading(true);
ttsPlayer.init();
const audioBuffer = await api.llm.speech({
model: ttsConfig.model,
input: text,
voice: ttsConfig.voice,
speed: ttsConfig.speed,
});
setSpeechStatus(true);
await ttsPlayer.play(audioBuffer, () => {
setSpeechStatus(false);
});
} catch (error) {
console.error("[OpenAI Speech]", error);
setSpeechStatus(false);
// Implement user-facing error notification here
if (typeof (error as Error).message === "string") {
showToast((error as Error).message);
}
} finally {
setSpeechLoading(false);
}
}
async function openaiSpeech(text: string) {
if (speechStatus) {
stopSpeech();
} else {
await playSpeech(text, config.ttsConfig);
}
}
return (
<>
<ListItem
@@ -88,23 +145,41 @@ export function TTSConfigList(props: {
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(
<div style={{ display: "flex", gap: "10px" }}>
<IconButton
aria={Locale.Chat.Actions.Speech}
icon={speechStatus ? <SpeakStopIcon /> : <SpeakIcon />}
text={
speechLoading
? "Loading..."
: speechStatus
? Locale.Chat.Actions.Stop
: Locale.Chat.Actions.Speech
}
onClick={() => {
openaiSpeech(
"NextChat,Unleash your imagination, experience the future of AI conversation.",
);
}}
/>
<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>
);
});
}}
>
{DEFAULT_TTS_VOICES.map((v, i) => (
<option value={v} key={i}>
{v}
</option>
))}
</Select>
</div>
</ListItem>
<ListItem
title={Locale.Settings.TTS.Speed.Title}

View File

@@ -523,15 +523,20 @@ const openaiModels = [
];
const googleModels = [
"gemini-1.0-pro", // Deprecated on 2/15/2025
"gemini-1.5-pro-latest",
"gemini-1.5-pro",
"gemini-1.5-pro-002",
"gemini-1.5-pro-exp-0827",
"gemini-1.5-flash-latest",
"gemini-1.5-flash-8b-latest",
"gemini-1.5-flash",
"gemini-1.5-flash-8b",
"gemini-1.5-flash-002",
"gemini-1.5-flash-exp-0827",
"learnlm-1.5-pro-experimental",
"gemini-exp-1114",
"gemini-exp-1121",
"gemini-exp-1206",
"gemini-2.0-flash",
"gemini-2.0-flash-exp",
@@ -628,18 +633,6 @@ const xAIModes = [
"grok-2-vision-1212",
"grok-2-vision",
"grok-2-vision-latest",
"grok-3-mini-fast-beta",
"grok-3-mini-fast",
"grok-3-mini-fast-latest",
"grok-3-mini-beta",
"grok-3-mini",
"grok-3-mini-latest",
"grok-3-fast-beta",
"grok-3-fast",
"grok-3-fast-latest",
"grok-3-beta",
"grok-3",
"grok-3-latest",
];
const chatglmModels = [

View File

@@ -83,7 +83,7 @@
"jest": "^29.7.0",
"jest-environment-jsdom": "^29.7.0",
"lint-staged": "^13.2.2",
"prettier": "^3.6.2",
"prettier": "^3.0.2",
"ts-node": "^10.9.2",
"tsx": "^4.16.0",
"typescript": "5.2.2",

View File

@@ -7076,10 +7076,10 @@ prettier-linter-helpers@^1.0.0:
dependencies:
fast-diff "^1.1.2"
prettier@^3.6.2:
version "3.6.2"
resolved "https://registry.yarnpkg.com/prettier/-/prettier-3.6.2.tgz#ccda02a1003ebbb2bfda6f83a074978f608b9393"
integrity sha512-I7AIg5boAr5R0FFtJ6rCfD+LFsWHp81dolrFD8S79U9tb8Az2nGrJncnMSnys+bpQJfRUzqs9hnA81OAA3hCuQ==
prettier@^3.0.2:
version "3.0.2"
resolved "https://registry.yarnpkg.com/prettier/-/prettier-3.0.2.tgz#78fcecd6d870551aa5547437cdae39d4701dca5b"
integrity sha512-o2YR9qtniXvwEZlOKbveKfDQVyqxbEIWn48Z8m3ZJjBjcCmUy3xZGIv+7AkaeuaTr6yPXJjwv07ZWlsWbEy1rQ==
pretty-format@^27.0.2:
version "27.5.1"