mirror of
https://github.com/lobehub/lobehub.git
synced 2026-09-20 04:56:13 +08:00
YuTengjing
191f3fe776
* 📝 docs: fix outdated content across the docs site Audited docs/ against the current codebase and fixed stale content that drifted after major refactors (Clerk/NextAuth → Better Auth, src/server → apps/server, src/{config,envs,locales} → packages/*, model-bank updates). - self-hosting/auth: mark removed NextAuth/Clerk pages with deprecation warnings; fix microsoft/zitadel alias claims and the Logto callback path - environment-variables & advanced: correct wrong defaults (S3_SET_ACL, AI_IMAGE_DEFAULT_IMAGE_NUM, index/proxy URLs), drop non-existent env vars and fictional feature flags, fix OIDC config guidance - development: update refactored paths, Better Auth, .mjs configs, remove the MSW section (msw is not a dependency) - providers & model examples: replace retired model ids with in-bank ones; fix comfyui frontmatter corruption - usage: rename Moderator→Orchestrator, GTD→Task, correct shortcut keys, channel capability tables, Feishu/Lark WebSocket mode - platform/migration: fix dead links, docker service name, npx/npm → bun EN and zh-CN pairs updated together. * 📝 docs: fix Logto callback path and AUTH_SECRET deprecation guidance - Revert Logto/Sealos callback URLs to /api/auth/callback/logto to match the runtime SSO redirectURI override - Narrow legacy auth Callout: AUTH_SECRET remains required for Better Auth; mark NEXT_AUTH_SECRET as deprecated in zh-CN * 📝 docs: refresh agent skills for locales, env, auth, and agentRun paths Align OSS agent guidance with post-refactor layout: - packages/locales/src/default + bun run i18n - packages/env/src for env schemas (@/envs alias) - spa-auth shell + src/routes/auth segments - chat agentRun/transports/hetero instead of aiChat * 📝 docs: document APP_URL as required for Better Auth base URL Self-hosted auth uses appEnv.APP_URL as baseURL, not request-header auto-detection. NEXT_PUBLIC_AUTH_URL remains deprecated. * 📝 docs: note self-host search provider setup for web search Built-in lobe-web-browsing needs no client plugin, but self-hosted servers still require SEARCH_PROVIDERS / SEARXNG_URL (default SearXNG). * 📝 docs: point feature guide welcome UI at AgentHome Opening message/questions on the agent chat page live in src/features/AgentHome, not Onboarding WelcomeMessage.
57 lines
2.8 KiB
Plaintext
57 lines
2.8 KiB
Plaintext
---
|
|
title: Conversation Translation
|
|
description: >-
|
|
Translate conversation content into any language with one click — real-time
|
|
display, configurable model. Break language barriers in your workflow.
|
|
tags:
|
|
- LobeHub
|
|
- Translation
|
|
- Real-Time Translation
|
|
- Multilingual
|
|
---
|
|
|
|
# Translate Conversation History
|
|
|
|
LobeHub lets you translate conversation content into a target language with a single click. Select a language, and the pre-configured AI model performs the translation and displays the results in real time within the chat window. No need to copy-paste into external tools — translation happens right where you're working.
|
|
|
|
<Image alt={'Translate Conversation'} cover src={'/blog/assetsc1d4290f05fe474dba74577409cad6e9.webp'} />
|
|
|
|
## Translate Content Within Conversations
|
|
|
|
Click the translate option on any message to convert it to your chosen language. The translation appears inline, so you can read the original and translated text side by side. Useful for:
|
|
|
|
- **Understanding responses** — When the Agent replies in a language you're less fluent in, translate to your preferred language.
|
|
- **Sharing with others** — Translate a conversation before sharing so recipients can read it in their language.
|
|
- **Learning** — Compare original and translated text to improve your language skills.
|
|
- **Cross-language collaboration** — Team members can work in their preferred language; translate as needed to stay aligned.
|
|
|
|
<Image alt={'Display Translated Conversation'} src={'/blog/assetsf3ccd42bf36b1c75f06f925ffe049f0c.webp'} />
|
|
|
|
## Configure Translation Model
|
|
|
|
You can specify which model to use for translation. A capable model produces more accurate and natural translations, especially for technical or nuanced content.
|
|
|
|
<Image alt={'Configure Translation Model'} src={'/blog/assets6541bab7e0047f9c5dbad98dc272d64d.webp'} />
|
|
|
|
- Open the **Settings** panel
|
|
- Navigate to **System Tasks** and find **Message Translation**
|
|
- Assign a **Model** to use for translation
|
|
|
|
**Tips:** Use a model with strong multilingual capability (e.g., GPT-4o, Claude, Gemini) for best results. Smaller or older models may produce rougher translations.
|
|
|
|
## Use Cases
|
|
|
|
**International teams** — Communicate in your language; translate key messages for colleagues who prefer another.
|
|
|
|
**Research and learning** — Read papers, articles, or documentation in the original language, then translate sections you need to understand deeply.
|
|
|
|
**Customer support** — Respond in the customer's language, or translate their message to understand the issue before replying.
|
|
|
|
**Content creation** — Draft in one language, translate to another for localization or multi-language publishing.
|
|
|
|
<Cards>
|
|
<Card href={'/docs/usage/agent/tts-stt'} title={'Text-to-Speech & Speech-to-Text'} />
|
|
|
|
<Card href={'/docs/usage/user-interface/appearance'} title={'Interface Appearance'} />
|
|
</Cards>
|