Skip to content

Commit 5d1ad58

Browse files
XimilalaXiangcursoragent
XimilalaXiang
and
cursoragent
committed
docs: add file transcription to docs site and landing page
- Add File Transcription feature card to docs homepage (EN/ZH) - Update "What's New" section title and add file transcription highlight - Add File column to provider comparison tables (EN/ZH) - Add file transcription feature card to landing page with i18n - Update hero description to mention file upload capability Co-authored-by: Cursor <cursoragent@cursor.com>
1 parent 68434ec commit 5d1ad58

5 files changed

Lines changed: 62 additions & 35 deletions

File tree

‎docs/guide/providers.md‎

Lines changed: 14 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -6,20 +6,20 @@ DeLive supports twelve ASR backends through a unified provider registry. Each pr
66
77
## Provider Comparison
88

9-
| Provider | Type | Transport | Audio | Streaming | Translation | Diarization |
10-
|----------|------|-----------|-------|-----------|-------------|-------------|
11-
| Soniox V4 | Cloud | WebSocket | MediaRecorder (WebM/Opus) | Yes | Yes | Yes |
12-
| Volcengine | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No |
13-
| ElevenLabs | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No |
14-
| Mistral AI | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No |
15-
| Gladia | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No |
16-
| Deepgram | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No |
17-
| AssemblyAI | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No |
18-
| Cloudflare Workers AI | Cloud | REST (batch) | AudioWorklet (PCM16) | No | No | No |
19-
| SiliconFlow | Cloud | REST (batch) | AudioWorklet (PCM16) | No | No | No |
20-
| Groq | Cloud | REST (batch) | AudioWorklet (PCM16) | No | No | No |
21-
| Local OpenAI | Local | REST (batch) | MediaRecorder (WebM/Opus) | No | No | No |
22-
| whisper.cpp | Local | REST (local) | AudioWorklet (PCM16) | No | No | No |
9+
| Provider | Type | Transport | Audio | Streaming | Translation | Diarization | File |
10+
|----------|------|-----------|-------|-----------|-------------|-------------|------|
11+
| Soniox V4 | Cloud | WebSocket | MediaRecorder (WebM/Opus) | Yes | Yes | Yes | Yes |
12+
| Volcengine | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No | Yes |
13+
| ElevenLabs | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No | Yes |
14+
| Mistral AI | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No | Yes |
15+
| Gladia | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No | Yes |
16+
| Deepgram | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No | Yes |
17+
| AssemblyAI | Cloud | WebSocket (via proxy) | AudioWorklet (PCM16) | Yes | No | No | Yes |
18+
| Cloudflare Workers AI | Cloud | REST (batch) | AudioWorklet (PCM16) | No | No | No | Yes |
19+
| SiliconFlow | Cloud | REST (batch) | AudioWorklet (PCM16) | No | No | No | Yes |
20+
| Groq | Cloud | REST (batch) | AudioWorklet (PCM16) | No | No | No | Yes |
21+
| Local OpenAI | Local | REST (batch) | MediaRecorder (WebM/Opus) | No | No | No | No |
22+
| whisper.cpp | Local | REST (local) | AudioWorklet (PCM16) | No | No | No | No |
2323

2424
## Execution Modes
2525

‎docs/index.md‎

Lines changed: 10 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -33,6 +33,9 @@ features:
3333
- icon: 🌐
3434
title: Open API & MCP Ecosystem
3535
details: Local REST API (8 endpoints), real-time WebSocket streaming, standalone MCP server for Claude Desktop and Cursor, Agent Skill definition, and Agent Skills for one-call transcription inside any agent.
36+
- icon: 📁
37+
title: File Transcription
38+
details: Upload audio or video files and transcribe them offline using ten cloud ASR engines. Supports speaker diarization, word-level timestamps, and multi-language detection.
3639
- icon: 🎨
3740
title: Five Themes, Light & Dark
3841
details: Cyan, Violet, Rose, Green, and Amber accent palettes — each with full light and dark mode. New persistent sidebar navigation and Command Palette (Ctrl+K).
@@ -253,9 +256,14 @@ features:
253256
</div>
254257

255258
<div class="whats-new">
256-
<h2>What's New in v2.1.0</h2>
257-
<p class="subtitle">Cloudflare Workers AI, Gladia, AI Correction enhancements, and more</p>
259+
<h2>What's New</h2>
260+
<p class="subtitle">File transcription, Cloudflare Workers AI, Gladia, AI Correction enhancements, and more</p>
258261
<div class="new-features">
262+
<div class="new-feature">
263+
<div class="icon">📁</div>
264+
<h3>File Transcription</h3>
265+
<p>Upload audio or video files and transcribe them offline. Ten cloud ASR engines supported — Soniox, Volcengine, ElevenLabs, Mistral, Gladia, Deepgram, AssemblyAI, Cloudflare, SiliconFlow, and Groq — with speaker diarization and word-level timestamps.</p>
266+
</div>
259267
<div class="new-feature">
260268
<div class="icon">☁️</div>
261269
<h3>Cloudflare Workers AI</h3>

‎docs/zh/guide/providers.md‎

Lines changed: 14 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -6,20 +6,20 @@ DeLive 通过统一的 Provider 注册机制支持十二种 ASR 后端。每个
66
77
## Provider 对比
88

9-
| Provider | 类型 | 传输方式 | 音频格式 | 流式 | 翻译 | 说话人分离 |
10-
|----------|------|---------|---------|------|------|-----------|
11-
| Soniox V4 | 云端 | WebSocket | MediaRecorder (WebM/Opus) | 是 | 是 | 是 |
12-
| 火山引擎 | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 |
13-
| ElevenLabs | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 |
14-
| Mistral AI | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 |
15-
| Gladia | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 |
16-
| Deepgram | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 |
17-
| AssemblyAI | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 |
18-
| Cloudflare Workers AI | 云端 | REST（批量） | AudioWorklet (PCM16) | 否 | 否 | 否 |
19-
| 硅基流动 | 云端 | REST（批量） | AudioWorklet (PCM16) | 否 | 否 | 否 |
20-
| Groq | 云端 | REST（批量） | AudioWorklet (PCM16) | 否 | 否 | 否 |
21-
| 本地 OpenAI | 本地 | REST（批量） | MediaRecorder (WebM/Opus) | 否 | 否 | 否 |
22-
| whisper.cpp | 本地 | REST（本地） | AudioWorklet (PCM16) | 否 | 否 | 否 |
9+
| Provider | 类型 | 传输方式 | 音频格式 | 流式 | 翻译 | 说话人分离 | 文件 |
10+
|----------|------|---------|---------|------|------|-----------|------|
11+
| Soniox V4 | 云端 | WebSocket | MediaRecorder (WebM/Opus) | 是 | 是 | 是 | 是 |
12+
| 火山引擎 | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 | 是 |
13+
| ElevenLabs | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 | 是 |
14+
| Mistral AI | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 | 是 |
15+
| Gladia | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 | 是 |
16+
| Deepgram | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 | 是 |
17+
| AssemblyAI | 云端 | WebSocket（经代理） | AudioWorklet (PCM16) | 是 | 否 | 否 | 是 |
18+
| Cloudflare Workers AI | 云端 | REST（批量） | AudioWorklet (PCM16) | 否 | 否 | 否 | 是 |
19+
| 硅基流动 | 云端 | REST（批量） | AudioWorklet (PCM16) | 否 | 否 | 否 | 是 |
20+
| Groq | 云端 | REST（批量） | AudioWorklet (PCM16) | 否 | 否 | 否 | 是 |
21+
| 本地 OpenAI | 本地 | REST（批量） | MediaRecorder (WebM/Opus) | 否 | 否 | 否 | 否 |
22+
| whisper.cpp | 本地 | REST（本地） | AudioWorklet (PCM16) | 否 | 否 | 否 | 否 |
2323

2424
## 执行模式
2525

‎docs/zh/index.md‎

Lines changed: 10 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -33,6 +33,9 @@ features:
3333
- icon: 🌐
3434
title: 开放 API 与 MCP 生态
3535
details: 本地 REST API（8 个端点）、实时 WebSocket 流、独立 MCP 服务器（支持 Claude Desktop 和 Cursor）、Agent Skill 定义、Agent Skills 一键调用转录 — AI 集成一步到位。
36+
- icon: 📁
37+
title: 文件转录
38+
details: 上传音频/视频文件，使用十种云端 ASR 引擎离线转录。支持说话人分离、词级时间戳和多语言检测。
3639
- icon: 🎨
3740
title: 五套主题，明暗切换
3841
details: 青蓝、紫罗兰、玫瑰、绿色、琥珀五种配色。全新持久化侧栏导航和命令面板（Ctrl+K）。
@@ -253,9 +256,14 @@ features:
253256
</div>
254257

255258
<div class="whats-new">
256-
<h2>v2.1.0 新特性</h2>
257-
<p class="subtitle">新增 Cloudflare Workers AI 和 Gladia 提供商、AI 纠错增强等</p>
259+
<h2>最新特性</h2>
260+
<p class="subtitle">文件转录、Cloudflare Workers AI、Gladia、AI 纠错增强等</p>
258261
<div class="new-features">
262+
<div class="new-feature">
263+
<div class="icon">📁</div>
264+
<h3>文件转录</h3>
265+
<p>上传音频/视频文件，使用十种云端 ASR 引擎离线转录 — Soniox、火山引擎、ElevenLabs、Mistral、Gladia、Deepgram、AssemblyAI、Cloudflare、硅基流动和 Groq。支持说话人分离和词级时间戳。</p>
266+
</div>
259267
<div class="new-feature">
260268
<div class="icon">☁️</div>
261269
<h3>Cloudflare Workers AI</h3>

‎landing/index.html‎

Lines changed: 14 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -277,7 +277,7 @@ <h1 class="font-sans text-5xl md:text-5xl lg:text-7xl leading-[1.05] tracking-wi
277277
</h1>
278278
<div class="speech-bubble mb-8 md:mb-10 max-w-lg">
279279
<p class="font-bold text-sm md:text-base" data-i18n="hero.desc">
280-
Capture system audio. Transcribe with twelve ASR backends. Review with AI — correction, summaries, chat, mind maps. All local-first.
280+
Capture system audio or upload files. Transcribe with twelve ASR backends. Review with AI — correction, summaries, chat, mind maps. All local-first.
281281
</p>
282282
</div>
283283
<div class="flex flex-col sm:flex-row gap-2 md:gap-2 text-sm md:text-sm lg:text-base">
@@ -379,6 +379,15 @@ <h3 class="font-sans text-xl md:text-2xl tracking-wide uppercase mb-2" data-i18n
379379
<p class="font-bold text-sm" data-i18n="f.themes.desc">Cyan, Violet, Rose, Green, and Amber — light and dark modes. Command Palette.</p>
380380
</div>
381381

382+
<!-- File Transcription -->
383+
<div class="comic-card p-4 md:p-6 reveal reveal-delay-3">
384+
<div class="icon-comic bg-boom mb-4">
385+
<svg class="w-6 h-6 text-white" fill="none" stroke="currentColor" stroke-width="2.5" viewBox="0 0 24 24"><path stroke-linecap="round" stroke-linejoin="round" d="M19.5 14.25v-2.625a3.375 3.375 0 00-3.375-3.375h-1.5A1.125 1.125 0 0113.5 7.125v-1.5a3.375 3.375 0 00-3.375-3.375H8.25m2.25 0H5.625c-.621 0-1.125.504-1.125 1.125v17.25c0 .621.504 1.125 1.125 1.125h12.75c.621 0 1.125-.504 1.125-1.125V11.25a9 9 0 00-9-9z"/></svg>
386+
</div>
387+
<h3 class="font-sans text-xl md:text-2xl tracking-wide uppercase mb-2" data-i18n="f.file.title">File Transcription!</h3>
388+
<p class="font-bold text-sm" data-i18n="f.file.desc">Upload audio/video files. Ten cloud ASR engines. Speaker diarization and word-level timestamps.</p>
389+
</div>
390+
382391
<!-- WebDAV Backup -->
383392
<div class="comic-card p-4 md:p-6 reveal reveal-delay-3">
384393
<div class="icon-comic bg-bam mb-4">
@@ -790,7 +799,7 @@ <h2 class="font-sans text-3xl md:text-5xl tracking-wide uppercase mb-4" data-i18
790799
en: {
791800
'nav.features':'Features','nav.showcase':'Showcase','nav.integrations':'Integrations','nav.download':'Download','nav.guide':'Guide','nav.download-btn':'Download',
792801
'hero.badge':'v2.1 — AI Review Desk','hero.title1':'Hear Everything.','hero.title2':'Review Smarter.',
793-
'hero.desc':'Capture system audio. Transcribe with twelve ASR backends. Review with AI — correction, summaries, chat, mind maps. All local-first.',
802+
'hero.desc':'Capture system audio or upload files. Transcribe with twelve ASR backends. Review with AI — correction, summaries, chat, mind maps. All local-first.',
794803
'hero.cta-download':'Download Free!','hero.cta-github':'GitHub','hero.cta-guide':'Guide',
795804
'features.label':'Capabilities','features.title':'Everything you need!',
796805
'features.desc':'Twelve ASR engines, AI-powered review, floating captions — all running locally.',
@@ -800,6 +809,7 @@ <h2 class="font-sans text-3xl md:text-5xl tracking-wide uppercase mb-4" data-i18
800809
'f.caption.title':'Floating Captions!','f.caption.desc':'Always-on-top draggable subtitle window. Source, translated, bilingual modes. Fully customizable font, color, shadow and background.',
801810
'f.api.title':'Open API & MCP!','f.api.desc':'REST API, WebSocket streaming, MCP server for Claude Desktop and Cursor.',
802811
'f.themes.title':'Five Themes!','f.themes.desc':'Cyan, Violet, Rose, Green, and Amber — light and dark modes. Command Palette.',
812+
'f.file.title':'File Transcription!','f.file.desc':'Upload audio/video files. Ten cloud ASR engines. Speaker diarization and word-level timestamps.',
803813
'f.backup.title':'Cloud Backup!','f.backup.desc':'WebDAV + S3-compatible. Nutstore, Nextcloud, Alist, Amazon S3, MinIO. Auto-create directories.',
804814
'showcase.label':'See it in action','showcase.title':'Built for how you work!',
805815
'showcase.desc':'From live transcription to AI-powered insights.',
@@ -843,7 +853,7 @@ <h2 class="font-sans text-3xl md:text-5xl tracking-wide uppercase mb-4" data-i18
843853
zh: {
844854
'nav.features':'功能','nav.showcase':'展示','nav.integrations':'生态','nav.download':'下载','nav.guide':'指南','nav.download-btn':'下载',
845855
'hero.badge':'v2.1 — AI 回顾工作台','hero.title1':'听见一切','hero.title2':'智能回顾',
846-
'hero.desc':'捕获系统音频，十二大 ASR 引擎实时转录，AI 纠错、总结、对话、思维导图。数据完全本地存储。',
856+
'hero.desc':'捕获系统音频或上传文件，十二大 ASR 引擎实时/离线转录，AI 纠错、总结、对话、思维导图。数据完全本地存储。',
847857
'hero.cta-download':'免费下载！','hero.cta-github':'GitHub','hero.cta-guide':'指南',
848858
'features.label':'核心能力','features.title':'你需要的一切！',
849859
'features.desc':'十二大 ASR 引擎、AI 驱动的回顾工具、浮动字幕 — 全部本地运行。',
@@ -853,6 +863,7 @@ <h2 class="font-sans text-3xl md:text-5xl tracking-wide uppercase mb-4" data-i18
853863
'f.caption.title':'浮动字幕！','f.caption.desc':'始终置顶、可拖拽。原文、翻译、双语模式。完全自定义字体、颜色、阴影和背景。',
854864
'f.api.title':'Open API & MCP！','f.api.desc':'REST API、WebSocket 推流、MCP Server。',
855865
'f.themes.title':'五种主题！','f.themes.desc':'青色、紫罗兰、玫瑰、绿色、琥珀 — 亮色和暗色模式。命令面板。',
866+
'f.file.title':'文件转录！','f.file.desc':'上传音频/视频文件，十种云端 ASR 引擎离线转录。支持说话人分离和词级时间戳。',
856867
'f.backup.title':'云端备份！','f.backup.desc':'WebDAV + S3 兼容。坚果云、Nextcloud、Alist、Amazon S3、MinIO。自动创建目录。',
857868
'showcase.label':'功能展示','showcase.title':'为你的工作方式而生！',
858869
'showcase.desc':'从实时转录到 AI 智能洞察。',

0 commit comments

Comments
 (0)