mirror of
https://github.com/Yidadaa/ChatGPT-Next-Web.git
synced 2025-08-09 11:19:50 +08:00
feat: tts
This commit is contained in:
@@ -13,7 +13,6 @@ import {
|
||||
LLMApi,
|
||||
LLMModel,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
MultimodalContent,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
@@ -88,9 +87,6 @@ export class QwenApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const messages = options.messages.map((v) => ({
|
||||
|
@@ -5,7 +5,6 @@ import {
|
||||
LLMApi,
|
||||
MultimodalContent,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import {
|
||||
useAccessStore,
|
||||
@@ -90,9 +89,6 @@ export class ClaudeApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
extractMessage(res: any) {
|
||||
console.log("[Response] claude response: ", res);
|
||||
|
@@ -15,7 +15,6 @@ import {
|
||||
LLMModel,
|
||||
MultimodalContent,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
import {
|
||||
@@ -80,9 +79,6 @@ export class ErnieApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const messages = options.messages.map((v) => ({
|
||||
|
@@ -14,7 +14,6 @@ import {
|
||||
LLMModel,
|
||||
MultimodalContent,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
import {
|
||||
@@ -82,9 +81,6 @@ export class DoubaoApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const messages = options.messages.map((v) => ({
|
||||
|
@@ -6,7 +6,6 @@ import {
|
||||
LLMModel,
|
||||
LLMUsage,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import { useAccessStore, useAppConfig, useChatStore } from "@/app/store";
|
||||
import { getClientConfig } from "@/app/config/client";
|
||||
@@ -67,9 +66,7 @@ export class GeminiProApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions): Promise<void> {
|
||||
const apiClient = this;
|
||||
let multimodal = false;
|
||||
|
@@ -13,7 +13,6 @@ import {
|
||||
LLMApi,
|
||||
LLMModel,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
import {
|
||||
@@ -63,9 +62,6 @@ export class SparkApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const messages: ChatOptions["messages"] = [];
|
||||
|
@@ -27,7 +27,6 @@ import {
|
||||
LLMUsage,
|
||||
MultimodalContent,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
import {
|
||||
@@ -77,9 +76,6 @@ export class MoonshotApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const messages: ChatOptions["messages"] = [];
|
||||
|
@@ -34,7 +34,6 @@ import {
|
||||
LLMUsage,
|
||||
MultimodalContent,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
import {
|
||||
@@ -187,47 +186,6 @@ export class ChatGPTApi implements LLMApi {
|
||||
}
|
||||
}
|
||||
|
||||
async transcription(options: TranscriptionOptions): Promise<string> {
|
||||
const formData = new FormData();
|
||||
formData.append("file", options.file, "audio.wav");
|
||||
formData.append("model", options.model ?? "whisper-1");
|
||||
if (options.language) formData.append("language", options.language);
|
||||
if (options.prompt) formData.append("prompt", options.prompt);
|
||||
if (options.response_format)
|
||||
formData.append("response_format", options.response_format);
|
||||
if (options.temperature)
|
||||
formData.append("temperature", options.temperature.toString());
|
||||
|
||||
console.log("[Request] openai audio transcriptions payload: ", options);
|
||||
|
||||
const controller = new AbortController();
|
||||
options.onController?.(controller);
|
||||
|
||||
try {
|
||||
const path = this.path(OpenaiPath.TranscriptionPath, options.model);
|
||||
const headers = getHeaders(true);
|
||||
const payload = {
|
||||
method: "POST",
|
||||
body: formData,
|
||||
signal: controller.signal,
|
||||
headers: headers,
|
||||
};
|
||||
|
||||
// make a fetch request
|
||||
const requestTimeoutId = setTimeout(
|
||||
() => controller.abort(),
|
||||
REQUEST_TIMEOUT_MS,
|
||||
);
|
||||
const res = await fetch(path, payload);
|
||||
clearTimeout(requestTimeoutId);
|
||||
const json = await res.json();
|
||||
return json.text;
|
||||
} catch (e) {
|
||||
console.log("[Request] failed to make a audio transcriptions request", e);
|
||||
throw e;
|
||||
}
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const modelConfig = {
|
||||
...useAppConfig.getState().modelConfig,
|
||||
|
@@ -9,7 +9,6 @@ import {
|
||||
LLMModel,
|
||||
MultimodalContent,
|
||||
SpeechOptions,
|
||||
TranscriptionOptions,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
import {
|
||||
@@ -94,9 +93,6 @@ export class HunyuanApi implements LLMApi {
|
||||
speech(options: SpeechOptions): Promise<ArrayBuffer> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
transcription(options: TranscriptionOptions): Promise<string> {
|
||||
throw new Error("Method not implemented.");
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const visionModel = isVisionModel(options.config.model);
|
||||
|
Reference in New Issue
Block a user