Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

docs: feature Subtitle Edit FunASR integration (#3461)

zhifu gao76e5927209c5
diff --git a/web-pages/product-site/content/legacy-manifest.json b/web-pages/product-site/content/legacy-manifest.json
index 0f946829b..aec2ea0ce 100644
--- a/web-pages/product-site/content/legacy-manifest.json
+++ b/web-pages/product-site/content/legacy-manifest.json
@@ -20,7 +20,7 @@
"blog/funasr-vs-whisper-benchmark.html": "b7b49adf24d20570abb09b733ce03d4a50a4a0e98e746b4a9320f453e01cce84",
"blog/funclip-v2-1-0-video-clipping-release.html": "88f6c44e5332d1746c4db0fc97d755ef82f12e46d8f1c1c0ad9351152ff9dfc1",
"blog/generate-subtitles-srt-vtt-from-audio-video.html": "dbaf77072a980c8c50f33cb74e9513dea5dba2d31bd802fade38dcb0bb97e849",
- "blog/index.html": "ff0057519f7b657ddf737987be2d5eb615286346153fb92fd16d7863ad11eefb",
+ "blog/index.html": "c7b584195fbb15ae797092e4b3305ee811822b6e86223e016f96c5497d0a4e8e",
"blog/japanese-speech-recognition.html": "90f1f3bee4dcd72e414c6cb1ef9c0e580d5b7107356bc4285ac801affbb64486",
"blog/lightweight-speech-recognition-cpu.html": "d6270066222ed5baef0df108e6a4155f4a87bb5482169f23f218794d371f3281",
"blog/punctuation-restoration-python.html": "6cd26e03bf75b4343afd7b351c2681ebd513b058fb549c5888802be9ff3a1229",
@@ -31,6 +31,7 @@
"blog/sensevoice-emotion-language-detection.html": "6cd2a98e7813921754d33af9b2898f83dc9b1139482a34f2d0bb665189da67ee",
"blog/speech-to-text-python-transcribe-audio.html": "273c5e6fc6581ae995489d59c9f011de93a6c15e31f08fff56595bc0e6fd866f",
"blog/speech-to-text-timestamps-python.html": "78364db117dfbce45b03739679764cec7ab1d0a860f321c67154f33392fc6b8d",
+ "blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html": "f8d5870b6cf9dbdfd4e943fdccb7ae8f091472f1dcbd46bd7db90bd36e3e7846",
"blog/voice-activity-detection-python.html": "9055206633caecb83c11031f273c8c9297852f44dfe50984e03ab59a7deda6b5",
"blog/which-funasr-model.html": "0109fe2d66f85c3cc917c822671ec0fb137247ee407f6c33459e6f2cadd05b5d",
"css/742.48d54c7d.css": "38906de250e9a46352e178d2744831db647ee8dfa8cb6d70cbe68f40e2dfcb5b",
@@ -38,7 +39,7 @@
"css/index.1682178c.css": "b5f6034ce886c25773928c114e4290d1c491a3d081677b488810198efd76b4e1",
"decoder.js": "f2023a28036b1ff58e5bdabbb72ea427f8faaf60e89acd78ff183c313bdb0a2c",
"donors.html": "eec6b789b29c27d372925ae0ad3e13d4c6e62978b3c38c4da9e3aec129f10934",
- "ecosystem.html": "6c547fd83f245652513fcd739db7d314cf8b3b6b9e4ce75b1840cff58039dab0",
+ "ecosystem.html": "1defb2b8de27bbb85290813f8f9263b96fe5b9c67c821165645fca26d52d19b6",
"en/blog/cantonese-speech-recognition.html": "b9bd146198206f781c37f341c370a690dc83cd7163334e34b4e7f65e69af8ff2",
"en/blog/chinese-speech-recognition.html": "16b68bd2a1122236c580c62275002ae2c0875ca14e32686e88d3b5ccfa9f56ef",
"en/blog/fun-asr-nano-guide.html": "1746c708bd0606188de4266d8255984dd9e14634af33c54ad65a5f05b767be1b",
@@ -55,7 +56,7 @@
"en/blog/funasr-vs-whisper-benchmark.html": "367d4a8a1cc09ac932c80cdad065127925c5e5f942a806ace683c16dc1132769",
"en/blog/funclip-v2-1-0-video-clipping-release.html": "229baf59adf2c3290541d9b3c8a6243992406ba84b712714e9d14599205cb1d4",
"en/blog/generate-subtitles-srt-vtt-from-audio-video.html": "bd81aa43c6a977f28dd3925861bf456002fbacfec0df0504b413daa64ae60dfa",
- "en/blog/index.html": "19080d45223511743fda663d076835dff88c9011d9840ee85d1a21dc754d5787",
+ "en/blog/index.html": "ac522ccc02a3df9688fa3ea21f13480f2ca4c996b7dcd4f66fbb28806775ccbe",
"en/blog/japanese-speech-recognition.html": "8b106563142c291d3b86fad79a51e9c8746417b7750430e91296cc90764e570f",
"en/blog/lightweight-speech-recognition-cpu.html": "0e02c0e0853b12613d32c250f593c05c2052f18231207b63ee01d6e6600a86f7",
"en/blog/punctuation-restoration-python.html": "d6e30049f48d9dc6e6bc22eb567830013e4161eca51215616738b675dd1ffc40",
@@ -66,10 +67,11 @@
"en/blog/sensevoice-emotion-language-detection.html": "35ea4c9fc89b95b7b0de75c6138058717271d22222d5d0c502add275c068c794",
"en/blog/speech-to-text-python-transcribe-audio.html": "225d4334c591d53aa126d4f31bc4eb0cbaf0afb63c2486c7c934757a0a3627b9",
"en/blog/speech-to-text-timestamps-python.html": "6a7f8368f757c9ea50e287db6db3191ebcbbfc914f9a869b9515648b2d69790b",
+ "en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html": "7c65a73bab1ff481d9b398476ea6440926546ba7122cc2cb64f5bda81fc039a2",
"en/blog/voice-activity-detection-python.html": "d12f5d0f4ae07c3434f6188d12f5603b8abb9578413b79133668638d1c5e18a7",
"en/blog/which-funasr-model.html": "1207180aa929a3aa51db136c1098f4edc8f07405e2b56fe033998bf996f8ec7f",
"en/donors.html": "eacb7f9434b1b29e13e9b0175bb9680556ee72ab4dbd155e68f9c912eb0212b1",
- "en/ecosystem.html": "e498a8740c1cdf757556b40941b77f470ad51fb744d29e98025b4293e7e96f2e",
+ "en/ecosystem.html": "3b7dc72e8925d60716e144ea8771ca433275cf1281ba29cb872d15fc7451e3f2",
"en/index.html": "4950bc2e0b337637300c5bcd45d1820d9636c4f1dab34e0ec8d3443be44bd277",
"en/llama-cpp.html": "dbfbd125ebbf07f7d923c91b122818f8b09484ce54c1e80eba66a89d22dfb5b4",
"en/models.html": "c2add621edc3aa63e6d49587f089ee5ac6c05faf5f68e14fef70a7a5ab443a4d",
@@ -84,6 +86,7 @@
"img/mxjs-bg.e085eb31.png": "773f9462b525ad6b74e96387217e543d238a12b2af7f6c0d089f745291079551",
"img/mxjs.6724be62.png": "9d398c1aa1e55de7b3d7729886d5f2866c31f00e82c3b36ea7740d02e60ee1aa",
"img/sstx-bg.d7e580c1.png": "33a6bd3159f3748244f3c27545314010a33bb7d9749c95be3fc24f0075741a62",
+ "img/subtitle-edit-speech-to-text.png": "3ea166b3dc21ab262418d40616852360e1c10aaba22a2365bfd4b1c238972e15",
"index.html": "95aa61940d7e48d3210899ec4b7d22bbd198ef7e3721b117e1e489f1e7b47b1a",
"index.js": "f10e5fff91ed36af5377609eefa067c7e22278d0dd8e558f065733ca99b93fd6",
"jessibuca.js": "02240fc0fdfa74ebe840cc6c818fc91a9c3cb830d9ebeddd9ca21b46168aa06f",
diff --git a/web-pages/product-site/legacy/blog/index.html b/web-pages/product-site/legacy/blog/index.html
index 578e2bfc2..2555d3f4f 100644
--- a/web-pages/product-site/legacy/blog/index.html
+++ b/web-pages/product-site/legacy/blog/index.html
@@ -42,13 +42,13 @@ p code,li code{background:var(--surface);padding:2px 6px;border-radius:5px;font-
.post-card p{margin:0;color:var(--text-soft);font-size:0.9rem}
.post-card .date{color:var(--text-muted);font-size:0.8rem}
.launch-feature{max-width:800px;margin:104px auto 0;padding:0 24px}.launch-feature a{display:grid;grid-template-columns:1fr auto;align-items:center;gap:20px;border:1px solid #bbf7d0;border-left:4px solid #047857;border-radius:8px;background:#f0fdf4;padding:20px 22px;color:var(--text)}.launch-feature a:hover{border-color:#047857;text-decoration:none}.launch-feature .date{font-size:.8rem;color:#047857;font-weight:600}.launch-feature h2{border:0;padding:0;margin:3px 0 5px;font-size:1.2rem}.launch-feature p{margin:0;font-size:.9rem}.launch-feature .action{font-weight:700;color:#1d4ed8;white-space:nowrap}
-.previous-release{padding-top:16px}.previous-release .post-card{margin-bottom:0}
+.previous-release{padding-top:16px}.previous-release .container{display:grid;grid-template-columns:1fr 1fr;gap:16px}.previous-release .post-card{margin-bottom:0}
footer{background:#0f172a;color:#94a3b8;padding:28px 0;text-align:center;font-size:0.8rem}
footer a{color:#94a3b8}
-@media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}.launch-feature a{grid-template-columns:1fr}.launch-feature .action{white-space:normal}}
+@media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}.launch-feature a{grid-template-columns:1fr}.launch-feature .action{white-space:normal}.previous-release .container{grid-template-columns:1fr}}
</style></head><body>
<nav class="nav"><div class="container"><a href="/" class="nav-logo">Fun<span>ASR</span></a><div class="nav-links"><a href="/#capabilities">核心能力</a><a href="/#usage">如何使用</a><a href="/#benchmark">性能</a><a href="/#demo">演示</a><a href="https://modelscope.github.io/FunASR/zh/" target="_blank">文档</a><a href="/quickstart.html">快速上手</a><a href="/models.html">模型</a><a href="/ecosystem.html">生态</a><a href="/blog/">技术博客</a><a href="/vs-whisper.html">对比 Whisper</a><a href="/donors.html">功德榜</a></div><a href="https://www.funasr.com/en/blog/" style="font-size:0.83rem;font-weight:500;color:var(--text-soft)">EN</a><a href="https://github.com/modelscope/FunASR" target="_blank" class="nav-btn">GitHub ★</a></div></nav>
<section class="launch-feature"><a href="/blog/funasr-v1-4-0-pypi-release.html"><div><span class="date">2026-07-31 · 正式 Release</span><h2>FunASR v1.4.0:更完整的 PyPI 安装包与更安全的 AutoModel 参数</h2><p>修复 SenseVoice 与 RWKV-BAT 包数据,提前拒绝 vda_model 误拼写,并提供 12 个带 SHA-256 的发布资产。</p></div><span class="action">查看发布与校验指南 →</span></a></section>
-<section class="previous-release"><div class="container"><a class="post-card" href="/blog/funclip-v2-1-0-video-clipping-release.html"><span class="date">2026-07-24</span><h2>FunClip v2.1.0:本地 AI 视频剪辑的首个版本化发布</h2><p>Paraformer、Fun-ASR-Nano、SenseVoice 与大模型剪辑,提供可校验、可回退的源码下载。</p></a></div></section>
+<section class="previous-release"><div class="container"><a class="post-card" href="/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"><span class="date">2026-08-03 · 生态集成</span><h2>Subtitle Edit 5.2:Fun-ASR Nano / SenseVoice 本地视频字幕</h2><p>在 Windows、macOS 与 Linux 的成熟字幕工作区中直接选择本地 ASR 引擎,支持 Q4、Q8、F16。</p></a><a class="post-card" href="/blog/funclip-v2-1-0-video-clipping-release.html"><span class="date">2026-07-24</span><h2>FunClip v2.1.0:本地 AI 视频剪辑的首个版本化发布</h2><p>Paraformer、Fun-ASR-Nano、SenseVoice 与大模型剪辑,提供可校验、可回退的源码下载。</p></a></div></section>
<article><div class="container"><h1>FunASR 技术博客</h1><p class="post-meta">语音识别部署、教程与最佳实践</p><a class="post-card" href="/blog/speech-to-text-timestamps-python.html"><span class="date">2026-06-23</span><h2>语音识别带时间戳(字级 timestamps)Python 实战:每个字精确到毫秒</h2><p>FunASR Paraformer 原生字级时间戳:每个字带 [起始毫秒,结束毫秒],一次调用即有。可做逐字高亮、点击跳转、字幕对齐。附真实实测+配对代码。</p></a><a class="post-card" href="/blog/punctuation-restoration-python.html"><span class="date">2026-06-23</span><h2>标点恢复 Python 实战:给无标点文本/ASR 结果自动加标点</h2><p>FunASR ct-punc 开源标点恢复,中英双语,3 行 Python 补全 ,。?(英文还做句首大写),也能一行挂到 ASR 上。附真实实测。</p></a><a class="post-card" href="/blog/chinese-speech-recognition.html"><span class="date">2026-06-22</span><h2>中文语音识别(普通话)Python 实战:用 FunASR 又快又准</h2><p>FunASR 专为中文打造:默认旗舰 Fun-ASR-Nano(CER 8.06%),CPU 用 SenseVoice(7.81%)/ Paraformer(10.18%,时间戳/热词),都远好于 Whisper(~20%)。3 行 Python。</p></a><a class="post-card" href="/blog/self-hosted-google-aws-azure-speech-to-text.html"><span class="date">2026-06-22</span><h2>自托管语音转文字:Google / AWS / Azure 云语音 API 的免费开源替代</h2><p>开源免费(MIT)、本地推理、不按分钟计费、数据不出内网、中文强,OpenAI 兼容改 base_url 即可迁移。附实测代码 + FunASR vs 云 API 对比 + 成本分析。</p></a><a class="post-card" href="/blog/voice-activity-detection-python.html"><span class="date">2026-06-22</span><h2>Python 语音活动检测(VAD):检测语音、去静音、按停顿切分音频</h2><p>FunASR fsmn-vad 3 行代码返回每段语音的起止毫秒。实测 13s 录音 0.12s 切成 2 段、去除 18% 静音;可去静音、切分长录音、给 Whisper 等做预处理防幻觉。</p></a><a class="post-card" href="/blog/japanese-speech-recognition.html"><span class="date">2026-06-22</span><h2>日语语音识别:SenseVoice 一个模型搞定日语转写+标点+情感</h2><p>同一段日语音频实测:SenseVoice 写对同音字 転売、自动加标点,Whisper-small 误为 天売、无标点。原生 ja 支持 + 自动语种识别 + 情感事件,3 行 Python。</p></a><a class="post-card" href="/blog/self-hosted-deepgram-assemblyai-alternative.html"><span class="date">2026-06-23</span><h2>自托管替代 Deepgram / AssemblyAI</h2><p>开源免费、自托管、音频不出本地、中文领先,自带 OpenAI 兼容 API——客户端只改 base_url 即可替代按分钟付费的云 STT。</p></a><a class="post-card" href="/blog/which-funasr-model.html"><span class="date">2026-06-23</span><h2>选哪个 FunASR 模型?Nano vs MLT-Nano vs SenseVoice vs Paraformer</h2><p>模型选型表 + 场景代码:中英日及中文方言/口音选旗舰 Nano,31 语种选独立 MLT-Nano,CPU 再选 SenseVoice 或 Paraformer。</p></a><a class="post-card" href="/blog/lightweight-speech-recognition-cpu.html"><span class="date">2026-06-22</span><h2>轻量语音识别:CPU 上约 250MB 跑中文 ASR</h2><p>单二进制 + 254MB q8 模型,无需 GPU/Python,CPU 0.16s,中文 CER 7.99%——比 whisper.cpp small 还小且准 3 倍。</p></a><a class="post-card" href="/blog/cantonese-speech-recognition.html"><span class="date">2026-06-21</span><h2>粤语语音识别:SenseVoice 原生支持粤语口语(Whisper 会转成普通话)</h2><p>同一段粤语音频实测:SenseVoice 保留 呢/唔/嘅,Whisper 转成普通话书面语。原生 yue 支持 + 自动语种识别,3 行 Python。</p></a><a class="post-card" href="/blog/funasr-vs-faster-whisper-chinese.html"><span class="date">2026-06-21</span><h2>FunASR vs faster-whisper:中文与粤语实测对比</h2><p>粤语被 faster-whisper 误判为普通话、日语同音字错;SenseVoice 原生支持粤语+语种识别,中文 CER 低约 2.7 倍。实测。</p></a><a class="post-card" href="/blog/funasr-llama-cpp-whisper-cpp-alternative.html"><span class="date">2026-06-20</span><h2>FunASR 跑进 llama.cpp:中文 ASR 的 whisper.cpp 替代品(CPU/零 Python)</h2><p>单个自包含二进制、内置 VAD、吃任意音频,下载即用转写中文;中文 CPU 上比 whisper.cpp 准约 2.7 倍。3 步实测。</p></a><a class="post-card" href="/blog/speech-to-text-python-transcribe-audio.html"><span class="date">2026-06-18</span><h2>Python 语音转文字:用 FunASR 本地免费转写音频</h2><p>几行 Python 把音频转成文本,带时间戳/说话人/批量;本地、免费、无 API key、中文强。</p></a><a class="post-card" href="/blog/generate-subtitles-srt-vtt-from-audio-video.html"><span class="date">2026-06-18</span><h2>用 FunASR 自动生成字幕:音频/视频一键出 SRT 和 VTT</h2><p>一行命令出 SRT,Python 同时导出 VTT,带说话人和真实时间戳;本地、免费、中文强。</p></a><a class="post-card" href="/blog/self-hosted-openai-whisper-api-alternative.html"><span class="date">2026-06-18</span><h2>自托管 OpenAI Whisper API 替代:FunASR 起兼容 /v1/audio/transcriptions 服务</h2><p>funasr-server 暴露 OpenAI 兼容接口,OpenAI SDK 只改 base_url 就能用;本地、免费、隐私、中文更准。</p></a><a class="post-card" href="/blog/funasr-cli-transcribe-command-line.html"><span class="date">2026-06-18</span><h2>用 FunASR 命令行转写音频:文本/JSON/SRT 字幕</h2><p>一行命令出文字/字幕/JSON,--spk 带说话人;还能 funasr-server 起 OpenAI 兼容 API。</p></a><a class="post-card" href="/blog/funasr-transcribe-long-audio.html"><span class="date">2026-06-17</span><h2>用 FunASR 转写超长音频:1 小时一次搞定</h2><p>Whisper 限 30 秒,FunASR 内置 VAD 一次吃下任意时长;实测 13 分钟 4.3 秒转完(186x)。</p></a><a class="post-card" href="/blog/funasr-realtime-streaming-asr.html"><span class="date">2026-06-17</span><h2>用 FunASR 实现实时流式语音识别(边说边出字)</h2><p>600ms 级低延迟流式 ASR:分块+cache 边说边出字,含 2-pass(流式+离线)最佳实践。</p></a><a class="post-card" href="/blog/sensevoice-emotion-language-detection.html"><span class="date">2026-06-17</span><h2>超越转写:用 SenseVoice 识别语言、情感与声学事件</h2><p>一次非自回归前向同时输出转写+语种+情感+音频事件,Whisper 做不到的四合一。</p></a><a class="post-card" href="/blog/funasr-speaker-diarization.html"><span class="date">2026-06-17</span><h2>用 FunASR 做说话人分离:谁在何时说了什么</h2><p>一次 generate 调用同时输出转写+说话人标签+时间戳,替代 pyannote+Whisper,无需 HF 授权。</p></a><a class="post-card" href="/blog/funasr-vs-whisper-benchmark.html"><span class="date">2026-06-16</span><h2>FunASR vs Whisper 实测对比:谁更快更准</h2><p>184 中文文件 H100 实测:SenseVoice 169.6x、CER 7.81%,完整速度+准确率数据。</p></a><a class="post-card" href="/blog/fun-asr-nano-guide.html"><span class="date">2026-06-16</span><h2>Fun-ASR-Nano 使用指南:800M 端到端语音识别大模型</h2><p>主力旗舰,中英日 + 7 大中文方言/26 种口音,热词/流式/说话人分离;31 语种请用 MLT-Nano。</p></a><a class="post-card" href="/blog/sensevoice-deployment-guide.html"><span class="date">2026-06-16</span><h2>SenseVoice 部署指南:比 Whisper 快 15 倍</h2><p>3 行代码跑通多语言识别,含语种/情感/事件检测、VAD、GPU/CPU。</p></a><p>更多:<a href="/quickstart.html">快速上手</a> · <a href="/models.html">模型</a></p></div></article>
<footer><div class="container">© 2024-2026 Tongyi Lab, Alibaba Group · <a href="https://github.com/modelscope/FunASR/blob/main/LICENSE">MIT License</a></div></footer></body></html>
diff --git a/web-pages/product-site/legacy/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html b/web-pages/product-site/legacy/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html
new file mode 100644
index 000000000..92ebae4fd
--- /dev/null
+++ b/web-pages/product-site/legacy/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html
@@ -0,0 +1,96 @@
+<!DOCTYPE html>
+<html lang="zh">
+<head>
+ <meta charset="utf-8">
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <title>Subtitle Edit 5.2:用 Fun-ASR Nano / SenseVoice 在本地生成视频字幕 | FunASR</title>
+ <meta name="description" content="Subtitle Edit v5.2.0-beta2 已内置 Crisp ASR Fun-ASR Nano 与 SenseVoice,可在 Windows、macOS 和 Linux 本地生成视频字幕。">
+ <meta name="keywords" content="Subtitle Edit,Fun-ASR Nano,SenseVoice,本地字幕,视频字幕,CrispASR,Windows,macOS,Linux">
+ <link rel="icon" href="/logo.png">
+ <meta property="og:title" content="Subtitle Edit 5.2:用 Fun-ASR Nano / SenseVoice 在本地生成视频字幕">
+ <meta property="og:description" content="在成熟字幕编辑器中直接选择 Fun-ASR Nano 或 SenseVoice,本地转写视频并继续校时、断句和导出。">
+ <meta property="og:type" content="article">
+ <meta property="og:url" content="https://www.funasr.com/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <meta property="og:image" content="https://www.funasr.com/img/subtitle-edit-speech-to-text.png">
+ <link rel="canonical" href="https://www.funasr.com/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link rel="alternate" hreflang="en" href="https://www.funasr.com/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link rel="alternate" hreflang="zh" href="https://www.funasr.com/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link rel="alternate" hreflang="x-default" href="https://www.funasr.com/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&amp;display=swap" rel="stylesheet">
+ <script type="application/ld+json">
+ {"@context":"https://schema.org","@type":"BlogPosting","headline":"Subtitle Edit 5.2:用 Fun-ASR Nano / SenseVoice 在本地生成视频字幕","description":"Subtitle Edit v5.2.0-beta2 已内置 Crisp ASR Fun-ASR Nano 与 SenseVoice,可在 Windows、macOS 和 Linux 本地生成视频字幕。","datePublished":"2026-08-03","dateModified":"2026-08-03","author":{"@type":"Organization","name":"FunASR / Tongyi Lab"},"publisher":{"@type":"Organization","name":"FunASR","logo":{"@type":"ImageObject","url":"https://www.funasr.com/logo.png"}},"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.funasr.com/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"},"image":"https://www.funasr.com/img/subtitle-edit-speech-to-text.png"}
+ </script>
+ <style>
+ :root{--primary:#2563eb;--primary-dark:#1d4ed8;--accent:#047857;--bg:#fff;--surface:#f8fafc;--border:#e2e8f0;--text:#0f172a;--text-soft:#475569;--text-muted:#94a3b8}
+ *{margin:0;padding:0;box-sizing:border-box}
+ body{font-family:'Inter',-apple-system,sans-serif;color:var(--text);line-height:1.7;background:var(--bg)}
+ a{color:var(--primary);text-decoration:none}a:hover{text-decoration:underline}
+ .container{max-width:800px;margin:0 auto;padding:0 24px}
+ .nav{position:fixed;top:0;left:0;right:0;z-index:100;background:rgba(255,255,255,.94);backdrop-filter:blur(12px);border-bottom:1px solid var(--border);padding:14px 0}
+ .nav .container{max-width:1120px;display:flex;align-items:center;gap:24px}
+ .nav-logo{font-size:1.2rem;font-weight:800;color:var(--text)}.nav-logo span{color:var(--primary)}
+ .nav-links{display:flex;gap:20px;margin-left:auto;flex-wrap:wrap}.nav-links a{font-size:.85rem;font-weight:500;color:var(--text-soft)}
+ .nav-btn{padding:7px 16px;background:var(--primary);color:#fff;border-radius:7px;font-size:.83rem;font-weight:600}
+ article{padding:116px 0 80px}
+ h1{font-size:2rem;font-weight:800;line-height:1.3;margin-bottom:14px}
+ h2{font-size:1.3rem;font-weight:700;margin:38px 0 14px;padding-top:18px;border-top:1px solid var(--border)}
+ p{margin-bottom:14px;color:var(--text-soft)}
+ ol,ul{margin:0 0 16px 22px;color:var(--text-soft)}li{margin-bottom:7px}
+ table{width:100%;border-collapse:collapse;margin:18px 0;font-size:.88rem}
+ th,td{padding:11px 12px;text-align:left;vertical-align:top;border-bottom:1px solid var(--border)}th{font-weight:600;background:var(--surface);color:var(--text)}
+ code{font-family:ui-monospace,Menlo,monospace}p code,li code,td code{background:var(--surface);padding:2px 6px;border-radius:5px;font-size:.85em;color:var(--primary-dark)}
+ .post-meta{color:var(--text-muted);font-size:.85rem;margin-bottom:22px}
+ .lead{font-size:1.05rem;color:var(--text);margin:22px 0}
+ figure{margin:0 0 26px}.hero-media{display:block;width:100%;aspect-ratio:1097/676;object-fit:cover;border-radius:8px;border:1px solid var(--border)}figcaption{font-size:.78rem;color:var(--text-muted);margin-top:8px}
+ .proof{border-left:4px solid var(--accent);background:#f0fdf4;padding:14px 16px;margin:18px 0;color:#14532d}
+ .cta{background:var(--surface);border:1px solid var(--border);border-radius:8px;padding:24px;margin:30px 0;text-align:center}.cta p{margin-bottom:16px}.cta a.btn{display:inline-block;padding:10px 22px;background:var(--primary);color:#fff;border-radius:7px;font-weight:600}
+ footer{background:#0f172a;color:#94a3b8;padding:28px 0;text-align:center;font-size:.8rem}footer a{color:#94a3b8}
+ @media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}h1{font-size:1.65rem}table{font-size:.8rem}th,td{padding:9px 8px}}
+ </style>
+</head>
+<body>
+<nav class="nav"><div class="container"><a href="/" class="nav-logo">Fun<span>ASR</span></a><div class="nav-links"><a href="/#capabilities">核心能力</a><a href="/#usage">如何使用</a><a href="/#benchmark">性能</a><a href="/#demo">演示</a><a href="https://modelscope.github.io/FunASR/zh/" target="_blank">文档</a><a href="/quickstart.html">快速上手</a><a href="/models.html">模型</a><a href="/ecosystem.html">生态</a><a href="/blog/">技术博客</a><a href="/vs-whisper.html">对比 Whisper</a><a href="/donors.html">功德榜</a></div><a href="/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html" style="font-size:.83rem;font-weight:500;color:var(--text-soft)">EN</a><a href="https://github.com/modelscope/FunASR" target="_blank" rel="noopener" class="nav-btn">GitHub ★</a></div></nav>
+<article><div class="container">
+ <h1>Subtitle Edit 5.2:用 Fun-ASR Nano / SenseVoice 在本地生成视频字幕</h1>
+ <p class="post-meta">2026-08-03 · FunASR 生态集成</p>
+ <figure>
+ <img class="hero-media" src="/img/subtitle-edit-speech-to-text.png" alt="Subtitle Edit Speech to text 视频字幕工作区">
+ <figcaption>Subtitle Edit 官方 Speech to text 工作区截图。截图展示转写界面;v5.2.0-beta2 的 Engine 下拉菜单还包含 Fun-ASR Nano 与 SenseVoice。</figcaption>
+ </figure>
+ <p class="lead"><a href="https://github.com/SubtitleEdit/subtitleedit" target="_blank" rel="noopener">Subtitle Edit</a> 是跨平台开源字幕编辑器。它的 <a href="https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2" target="_blank" rel="noopener">v5.2.0-beta2</a> 已包含 <code>Crisp ASR Fun-ASR Nano</code> 和 <code>Crisp ASR SenseVoice</code> 两个本地语音识别引擎,可在 Windows、macOS 与 Linux 里从视频直接生成字幕,再继续校时、断句和导出。</p>
+ <div class="proof"><strong>版本说明:</strong>当前是 beta 版本,适合先用实际视频验证工作流,再决定是否用于生产。本文只描述 v5.2.0-beta2 exact tag 中可核验的能力。</div>
+
+ <h2>三步开始本地转写</h2>
+ <ol>
+ <li>安装或解压 Subtitle Edit v5.2.0-beta2,并打开待处理的视频。</li>
+ <li>进入 <code>Video → Audio to text</code>。</li>
+ <li>在 Engine 中选择 <code>Crisp ASR Fun-ASR Nano</code> 或 <code>Crisp ASR SenseVoice</code>,选择语言和模型精度后开始转写。</li>
+ </ol>
+ <p>整个流程位于 Subtitle Edit 的字幕工作区内,无需把音频上传到云端。生成结果可继续使用 Subtitle Edit 的时间轴、波形、字幕格式与质检能力。</p>
+
+ <h2>两个后端怎么选</h2>
+ <table>
+ <thead><tr><th>引擎</th><th>语言</th><th>可选量化与下载体积</th><th>适合场景</th></tr></thead>
+ <tbody>
+ <tr><td><a href="/go/fun-asr">Fun-ASR Nano</a></td><td>中文、粤语、英语、日语、韩语</td><td>Q4 0.90 GB<br>Q8 1.27 GB<br>F16 1.98 GB</td><td>更看重转写能力,设备内存充足</td></tr>
+ <tr><td><a href="/go/sensevoice">SenseVoice</a></td><td>自动检测,以及中文、粤语、英语、日语、韩语</td><td>Q4 136 MB<br>Q8 252 MB<br>F16 469 MB</td><td>轻量部署,并需要原生语种、情感或音频事件标签</td></tr>
+ </tbody>
+ </table>
+ <p>以上语言列表和模型体积来自 v5.2.0-beta2 的 <a href="https://github.com/SubtitleEdit/subtitleedit/blob/v5.2.0-beta2/src/ui/Features/Video/SpeechToText/Engines/CrispAsrFunAsrNano.cs" target="_blank" rel="noopener">Fun-ASR Nano engine source</a> 与 <a href="https://github.com/SubtitleEdit/subtitleedit/blob/v5.2.0-beta2/src/ui/Features/Video/SpeechToText/Engines/CrispAsrSenseVoice.cs" target="_blank" rel="noopener">SenseVoice engine source</a>。Q4 更省内存,Q8 在体积和精度之间折中,F16 体积最大。</p>
+
+ <h2>这次 beta 更新核验了什么</h2>
+ <p><a href="https://github.com/SubtitleEdit/subtitleedit/pull/13063" target="_blank" rel="noopener">Subtitle Edit PR #13063</a> 更新了 CrispASR 运行时,并记录了 SenseVoice 在 Apple Metal 路径上的转写验证。该 PR 还加入了其他引擎;Fun-ASR Nano 和 SenseVoice 后端本身已存在于项目中,因此这里不把 #13063 表述成“首次接入”。</p>
+ <ul>
+ <li>Release 提供 Windows、macOS 和 Linux 下载资产。</li>
+ <li>Fun-ASR Nano 与 SenseVoice 的三个模型精度都在 exact tag 源码中列出。</li>
+ <li>本地工作流把识别、字幕校时、断句和格式导出放在同一个桌面工具里。</li>
+ </ul>
+
+ <div class="cta">
+ <p>先用短视频和目标语言验证时间轴与文本质量,再处理长视频。遇到问题时请同时附上操作系统、引擎、模型精度和可复现片段。</p>
+ <a class="btn" href="https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2" target="_blank" rel="noopener">下载 Subtitle Edit v5.2.0-beta2</a>
+ </div>
+</div></article>
+<footer><div class="container">© 2024-2026 Tongyi Lab, Alibaba Group · <a href="https://github.com/modelscope/FunASR/blob/main/LICENSE">MIT License</a></div></footer>
+</body>
+</html>
diff --git a/web-pages/product-site/legacy/ecosystem.html b/web-pages/product-site/legacy/ecosystem.html
index 634c215eb..a10d5a0f2 100644
--- a/web-pages/product-site/legacy/ecosystem.html
+++ b/web-pages/product-site/legacy/ecosystem.html
@@ -60,11 +60,11 @@ pre{background:#1e293b;color:#e2e8f0;padding:18px;border-radius:10px;overflow-x:
.cta a.btn.outline{background:transparent;color:var(--primary);border:1px solid var(--primary)}
footer{background:#0f172a;color:#94a3b8;padding:32px 0;font-size:0.82rem;text-align:center;margin-top:60px}
footer a{color:#60a5fa}
-@media(max-width:640px){h1{font-size:1.5rem}.stat-bar{gap:20px}.stat-num{font-size:1.5rem}.card-grid{grid-template-columns:1fr}}
+@media(max-width:640px){.nav-links{display:none}.nav-logo{margin-right:auto}h1{font-size:1.5rem}.stat-bar{gap:20px}.stat-num{font-size:1.5rem}.card-grid{grid-template-columns:1fr}}
</style>
</head>
<body>
-<nav class="nav"><div class="container"><a class="nav-logo" href="./">Fun<span>ASR</span></a><div class="nav-links"><a href="/#capabilities">核心能力</a><a href="/#usage">如何使用</a><a href="/#benchmark">性能</a><a href="/#demo">演示</a><a href="https://modelscope.github.io/FunASR/zh/" target="_blank">文档</a><a href="quickstart.html">快速上手</a><a href="models.html">模型</a><a href="ecosystem.html">生态</a><a href="/blog/">技术博客</a><a href="vs-whisper.html">对比 Whisper</a><a href="/donors.html">功德榜</a><a href="en/ecosystem.html" style="font-size:0.85rem;font-weight:500;color:var(--text-soft);text-decoration:none">EN</a><a href="https://github.com/modelscope/FunASR" target="_blank" class="nav-btn">GitHub ★</a></div></div></nav>
+<nav class="nav"><div class="container"><a class="nav-logo" href="./">Fun<span>ASR</span></a><div class="nav-links"><a href="/#capabilities">核心能力</a><a href="/#usage">如何使用</a><a href="/#benchmark">性能</a><a href="/#demo">演示</a><a href="https://modelscope.github.io/FunASR/zh/" target="_blank">文档</a><a href="quickstart.html">快速上手</a><a href="models.html">模型</a><a href="ecosystem.html">生态</a><a href="/blog/">技术博客</a><a href="vs-whisper.html">对比 Whisper</a><a href="/donors.html">功德榜</a></div><a href="en/ecosystem.html" style="font-size:0.85rem;font-weight:500;color:var(--text-soft);text-decoration:none">EN</a><a href="https://github.com/modelscope/FunASR" target="_blank" class="nav-btn">GitHub ★</a></div></nav>
<article>
<div class="container">
@@ -94,6 +94,12 @@ footer a{color:#60a5fa}
<div><span class="card-tag">实时转写</span><span class="card-tag">SenseVoiceSmall</span></div>
</div>
<div class="card">
+<div class="card-title"><a href="https://github.com/SubtitleEdit/subtitleedit">Subtitle Edit</a></div>
+<div class="card-stars">13.7K+ stars</div>
+<div class="card-desc"><a href="https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2">v5.2.0-beta2</a> 已提供 Fun-ASR Nano 与 SenseVoice 本地视频字幕引擎,覆盖 Windows、macOS、Linux,并提供 Q4、Q8、F16 模型。<a href="https://github.com/SubtitleEdit/subtitleedit/pull/13063">PR #13063</a> 更新 CrispASR 运行时并核验 SenseVoice Metal 路径;<a href="/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">查看使用与选型</a>。</div>
+<div><span class="card-tag">视频字幕</span><span class="card-tag">Fun-ASR Nano</span><span class="card-tag">SenseVoice</span></div>
+</div>
+<div class="card">
<div class="card-title"><a href="https://github.com/jianchang512/pyvideotrans">pyVideoTrans</a></div>
<div class="card-stars">17.6K stars</div>
<div class="card-desc">视频翻译工具。使用 FunASR 进行中文语音识别,自动生成和翻译字幕。</div>
diff --git a/web-pages/product-site/legacy/en/blog/index.html b/web-pages/product-site/legacy/en/blog/index.html
index 8e34983df..203ebf217 100644
--- a/web-pages/product-site/legacy/en/blog/index.html
+++ b/web-pages/product-site/legacy/en/blog/index.html
@@ -42,13 +42,13 @@ p code,li code{background:var(--surface);padding:2px 6px;border-radius:5px;font-
.post-card p{margin:0;color:var(--text-soft);font-size:0.9rem}
.post-card .date{color:var(--text-muted);font-size:0.8rem}
.launch-feature{max-width:800px;margin:104px auto 0;padding:0 24px}.launch-feature a{display:grid;grid-template-columns:1fr auto;align-items:center;gap:20px;border:1px solid #bbf7d0;border-left:4px solid #047857;border-radius:8px;background:#f0fdf4;padding:20px 22px;color:var(--text)}.launch-feature a:hover{border-color:#047857;text-decoration:none}.launch-feature .date{font-size:.8rem;color:#047857;font-weight:600}.launch-feature h2{border:0;padding:0;margin:3px 0 5px;font-size:1.2rem}.launch-feature p{margin:0;font-size:.9rem}.launch-feature .action{font-weight:700;color:#1d4ed8;white-space:nowrap}
-.previous-release{padding-top:16px}.previous-release .post-card{margin-bottom:0}
+.previous-release{padding-top:16px}.previous-release .container{display:grid;grid-template-columns:1fr 1fr;gap:16px}.previous-release .post-card{margin-bottom:0}
footer{background:#0f172a;color:#94a3b8;padding:28px 0;text-align:center;font-size:0.8rem}
footer a{color:#94a3b8}
-@media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}.launch-feature a{grid-template-columns:1fr}.launch-feature .action{white-space:normal}}
+@media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}.launch-feature a{grid-template-columns:1fr}.launch-feature .action{white-space:normal}.previous-release .container{grid-template-columns:1fr}}
</style></head><body>
<nav class="nav"><div class="container"><a href="/en/" class="nav-logo">Fun<span>ASR</span></a><div class="nav-links"><a href="/en/#capabilities">Capabilities</a><a href="/en/#usage">How to Use</a><a href="/en/#benchmark">Benchmark</a><a href="/en/#demo">Demo</a><a href="https://modelscope.github.io/FunASR/" target="_blank">Docs</a><a href="/en/quickstart.html">Quickstart</a><a href="/en/models.html">Models</a><a href="/en/ecosystem.html">Ecosystem</a><a href="/en/blog/">Blog</a><a href="/en/vs-whisper.html">vs Whisper</a><a href="/en/donors.html">Thanks</a></div><a href="https://www.funasr.com/blog/" style="font-size:0.83rem;font-weight:500;color:var(--text-soft)">中文</a><a href="https://github.com/modelscope/FunASR" target="_blank" class="nav-btn">GitHub ★</a></div></nav>
<section class="launch-feature"><a href="/en/blog/funasr-v1-4-0-pypi-release.html"><div><span class="date">July 31, 2026 · Stable release</span><h2>FunASR v1.4.0: Complete PyPI Packages and Safer AutoModel Arguments</h2><p>SenseVoice and RWKV-BAT package-data fixes, an early vda_model typo guard, and 12 SHA-256-addressed release assets.</p></div><span class="action">Read the release and verification guide →</span></a></section>
-<section class="previous-release"><div class="container"><a class="post-card" href="/en/blog/funclip-v2-1-0-video-clipping-release.html"><span class="date">July 24, 2026</span><h2>FunClip v2.1.0: The First Versioned Local AI Video-Clipping Release</h2><p>Paraformer, Fun-ASR-Nano, SenseVoice, and LLM clipping in verifiable, rollback-ready source downloads.</p></a></div></section>
+<section class="previous-release"><div class="container"><a class="post-card" href="/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"><span class="date">August 3, 2026 · Ecosystem</span><h2>Subtitle Edit 5.2: Local Video Subtitles with Fun-ASR Nano or SenseVoice</h2><p>Select a local ASR engine inside a mature subtitle workspace on Windows, macOS, or Linux, with Q4, Q8, and F16 models.</p></a><a class="post-card" href="/en/blog/funclip-v2-1-0-video-clipping-release.html"><span class="date">July 24, 2026</span><h2>FunClip v2.1.0: The First Versioned Local AI Video-Clipping Release</h2><p>Paraformer, Fun-ASR-Nano, SenseVoice, and LLM clipping in verifiable, rollback-ready source downloads.</p></a></div></section>
<article><div class="container"><h1>FunASR Blog</h1><p class="post-meta">Speech recognition deployment, tutorials and best practices</p><a class="post-card" href="/en/blog/speech-to-text-timestamps-python.html"><span class="date">2026-06-23</span><h2>Speech-to-Text with Word/Character-Level Timestamps in Python</h2><p>FunASR Paraformer gives native character timestamps: every char has [start_ms, end_ms] in one call. Build word highlighting, click-to-seek, subtitle alignment. Real output + pairing code.</p></a><a class="post-card" href="/en/blog/punctuation-restoration-python.html"><span class="date">2026-06-23</span><h2>Punctuation Restoration in Python — Add Punctuation to Text / ASR Output</h2><p>FunASR ct-punc: open-source bilingual (zh+en) punctuation restoration. 3 lines of Python to add ,。? (and capitalize English), or attach to ASR in one line. Real output.</p></a><a class="post-card" href="/en/blog/chinese-speech-recognition.html"><span class="date">2026-06-22</span><h2>Chinese (Mandarin) Speech Recognition in Python — Fast &amp; Accurate with FunASR</h2><p>Purpose-built for Chinese: default flagship Fun-ASR-Nano (CER 8.06%), with SenseVoice (7.81%) / Paraformer (10.18%, timestamps/hotwords) for CPU — all far better than Whisper (~20%).</p></a><a class="post-card" href="/en/blog/self-hosted-google-aws-azure-speech-to-text.html"><span class="date">2026-06-22</span><h2>Self-Hosted Speech-to-Text — Free Alternative to Google / AWS / Azure Cloud Speech APIs</h2><p>Open-source (MIT), local inference, no per-minute billing, audio stays on your network, strong Chinese, OpenAI-compatible (migrate via base_url). Runnable code + FunASR vs cloud comparison + cost analysis.</p></a><a class="post-card" href="/en/blog/voice-activity-detection-python.html"><span class="date">2026-06-22</span><h2>Voice Activity Detection in Python — Detect Speech, Remove Silence, Split Audio</h2><p>FunASR fsmn-vad returns millisecond speech spans in 3 lines. Measured: a 13s clip split into 2 segments in 0.12s, 18% silence removed. Trim silence, split long audio, preprocess Whisper to cut hallucinations.</p></a><a class="post-card" href="/en/blog/japanese-speech-recognition.html"><span class="date">2026-06-22</span><h2>Japanese Speech Recognition in Python — SenseVoice: Transcription + Punctuation + Emotion in One Pass</h2><p>Real side-by-side on one Japanese clip: SenseVoice writes 転売 correctly and adds punctuation; Whisper-small gives 天売 with none. Native ja support + auto language ID + emotion/events, 3 lines of Python.</p></a><a class="post-card" href="/en/blog/self-hosted-deepgram-assemblyai-alternative.html"><span class="date">2026-06-23</span><h2>Self-Hosted Deepgram / AssemblyAI Alternative</h2><p>Open-source, free, self-hosted, audio stays local, Chinese-leading, with an OpenAI-compatible API — replace per-minute cloud STT by changing base_url.</p></a><a class="post-card" href="/en/blog/which-funasr-model.html"><span class="date">2026-06-23</span><h2>Which FunASR Model? Nano vs MLT-Nano vs SenseVoice vs Paraformer</h2><p>A decision table with code: flagship Nano for zh/en/ja plus Chinese dialects/accents, separate MLT-Nano for 31 languages, and CPU choices SenseVoice or Paraformer.</p></a><a class="post-card" href="/en/blog/lightweight-speech-recognition-cpu.html"><span class="date">2026-06-22</span><h2>Lightweight Speech Recognition: Chinese ASR in ~250MB on CPU</h2><p>One binary + a 254MB q8 model, no GPU/Python, 0.16s on CPU, 7.99% CER — smaller than whisper.cpp small and ~3x more accurate.</p></a><a class="post-card" href="/en/blog/cantonese-speech-recognition.html"><span class="date">2026-06-21</span><h2>Cantonese Speech Recognition in Python — SenseVoice Keeps Real Cantonese (Whisper Doesn't)</h2><p>Real side-by-side on one Cantonese clip: SenseVoice keeps 呢/唔/嘅, Whisper rewrites to Mandarin. Native yue support + auto language ID, 3 lines of Python.</p></a><a class="post-card" href="/en/blog/funasr-vs-faster-whisper-chinese.html"><span class="date">2026-06-21</span><h2>FunASR vs faster-whisper: Chinese &amp; Cantonese Compared</h2><p>faster-whisper mislabels Cantonese as Mandarin + Japanese homophone errors; SenseVoice handles Cantonese natively, ~2.7x lower CER on Chinese.</p></a><a class="post-card" href="/en/blog/funasr-llama-cpp-whisper-cpp-alternative.html"><span class="date">2026-06-20</span><h2>FunASR on llama.cpp — a whisper.cpp Alternative for Chinese ASR (CPU, no Python)</h2><p>One self-contained binary, built-in VAD, any audio — download and transcribe Chinese; ~2.7x more accurate than whisper.cpp on CPU.</p></a><a class="post-card" href="/en/blog/speech-to-text-python-transcribe-audio.html"><span class="date">2026-06-18</span><h2>Speech to Text in Python with FunASR</h2><p>Transcribe audio in a few lines of Python — timestamps, speakers, batching. Local, free, no API key.</p></a><a class="post-card" href="/en/blog/generate-subtitles-srt-vtt-from-audio-video.html"><span class="date">2026-06-18</span><h2>Auto-Generate Subtitles (SRT &amp; VTT) from Audio or Video with FunASR</h2><p>One command for SRT, Python for VTT too, with speaker labels and real timestamps. Local, free, strong on Chinese.</p></a><a class="post-card" href="/en/blog/self-hosted-openai-whisper-api-alternative.html"><span class="date">2026-06-18</span><h2>Self-Hosted OpenAI Whisper API Alternative with FunASR</h2><p>funasr-server exposes an OpenAI-compatible /v1/audio/transcriptions; the OpenAI SDK works by changing only base_url. Local, free, private.</p></a><a class="post-card" href="/en/blog/funasr-cli-transcribe-command-line.html"><span class="date">2026-06-18</span><h2>Transcribe Audio from the Command Line with FunASR</h2><p>One command -> text/SRT/JSON, --spk for speakers; plus funasr-server for an OpenAI-compatible API.</p></a><a class="post-card" href="/en/blog/funasr-transcribe-long-audio.html"><span class="date">2026-06-17</span><h2>Transcribe Long Audio with FunASR: Hours in One Call</h2><p>Whisper caps at 30s; FunASR ingests any length via built-in VAD - 13 min in 4.3s (186x).</p></a><a class="post-card" href="/en/blog/funasr-realtime-streaming-asr.html"><span class="date">2026-06-17</span><h2>Real-Time Streaming Speech-to-Text with FunASR</h2><p>~600ms low-latency streaming ASR with chunks + cache, plus the 2-pass (streaming + offline) best practice.</p></a><a class="post-card" href="/en/blog/sensevoice-emotion-language-detection.html"><span class="date">2026-06-17</span><h2>Beyond Transcription: Language, Emotion & Audio Events with SenseVoice</h2><p>Transcription + language + emotion + audio events in one pass — the 4-in-1 Whisper cannot do.</p></a><a class="post-card" href="/en/blog/funasr-speaker-diarization.html"><span class="date">2026-06-17</span><h2>Speaker Diarization with FunASR: Who Spoke When</h2><p>Transcription + speaker labels + timestamps in one generate() call. A pyannote+Whisper alternative, no HF gated access.</p></a><a class="post-card" href="/en/blog/funasr-vs-whisper-benchmark.html"><span class="date">2026-06-16</span><h2>FunASR vs Whisper: Real Chinese ASR Benchmark</h2><p>Measured on 184 Chinese files (H100): SenseVoice 169.6x, 7.81% CER — full speed & accuracy data.</p></a><a class="post-card" href="/en/blog/fun-asr-nano-guide.html"><span class="date">2026-06-16</span><h2>Fun-ASR-Nano Guide: 800M End-to-End ASR LLM</h2><p>Flagship for zh/en/ja plus 7 Chinese dialect groups and 26 accents; choose MLT-Nano for 31 languages.</p></a><a class="post-card" href="/en/blog/sensevoice-deployment-guide.html"><span class="date">2026-06-16</span><h2>SenseVoice Deployment Guide: 15x Faster Than Whisper</h2><p>Multilingual ASR in 3 lines, with language/emotion/event tags, VAD, GPU/CPU.</p></a><p>More: <a href="/en/quickstart.html">Quickstart</a> · <a href="/en/models.html">Models</a></p></div></article>
<footer><div class="container">© 2024-2026 Tongyi Lab, Alibaba Group · <a href="https://github.com/modelscope/FunASR/blob/main/LICENSE">MIT License</a></div></footer></body></html>
diff --git a/web-pages/product-site/legacy/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html b/web-pages/product-site/legacy/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html
new file mode 100644
index 000000000..7771d4af8
--- /dev/null
+++ b/web-pages/product-site/legacy/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html
@@ -0,0 +1,96 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="utf-8">
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <title>Subtitle Edit 5.2: Generate Local Video Subtitles with Fun-ASR Nano or SenseVoice | FunASR</title>
+ <meta name="description" content="Subtitle Edit v5.2.0-beta2 includes Crisp ASR Fun-ASR Nano and SenseVoice for local video subtitle generation on Windows, macOS, and Linux.">
+ <meta name="keywords" content="Subtitle Edit,Fun-ASR Nano,SenseVoice,local subtitles,video subtitles,CrispASR,Windows,macOS,Linux">
+ <link rel="icon" href="/logo.png">
+ <meta property="og:title" content="Subtitle Edit 5.2: Generate Local Video Subtitles with Fun-ASR Nano or SenseVoice">
+ <meta property="og:description" content="Choose Fun-ASR Nano or SenseVoice inside a mature subtitle editor, transcribe video locally, then time, segment, and export the subtitles.">
+ <meta property="og:type" content="article">
+ <meta property="og:url" content="https://www.funasr.com/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <meta property="og:image" content="https://www.funasr.com/img/subtitle-edit-speech-to-text.png">
+ <link rel="canonical" href="https://www.funasr.com/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link rel="alternate" hreflang="en" href="https://www.funasr.com/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link rel="alternate" hreflang="zh" href="https://www.funasr.com/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link rel="alternate" hreflang="x-default" href="https://www.funasr.com/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">
+ <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&amp;display=swap" rel="stylesheet">
+ <script type="application/ld+json">
+ {"@context":"https://schema.org","@type":"BlogPosting","headline":"Subtitle Edit 5.2: Generate Local Video Subtitles with Fun-ASR Nano or SenseVoice","description":"Subtitle Edit v5.2.0-beta2 includes Crisp ASR Fun-ASR Nano and SenseVoice for local video subtitle generation on Windows, macOS, and Linux.","datePublished":"2026-08-03","dateModified":"2026-08-03","author":{"@type":"Organization","name":"FunASR / Tongyi Lab"},"publisher":{"@type":"Organization","name":"FunASR","logo":{"@type":"ImageObject","url":"https://www.funasr.com/logo.png"}},"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.funasr.com/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html"},"image":"https://www.funasr.com/img/subtitle-edit-speech-to-text.png"}
+ </script>
+ <style>
+ :root{--primary:#2563eb;--primary-dark:#1d4ed8;--accent:#047857;--bg:#fff;--surface:#f8fafc;--border:#e2e8f0;--text:#0f172a;--text-soft:#475569;--text-muted:#94a3b8}
+ *{margin:0;padding:0;box-sizing:border-box}
+ body{font-family:'Inter',-apple-system,sans-serif;color:var(--text);line-height:1.7;background:var(--bg)}
+ a{color:var(--primary);text-decoration:none}a:hover{text-decoration:underline}
+ .container{max-width:800px;margin:0 auto;padding:0 24px}
+ .nav{position:fixed;top:0;left:0;right:0;z-index:100;background:rgba(255,255,255,.94);backdrop-filter:blur(12px);border-bottom:1px solid var(--border);padding:14px 0}
+ .nav .container{max-width:1120px;display:flex;align-items:center;gap:24px}
+ .nav-logo{font-size:1.2rem;font-weight:800;color:var(--text)}.nav-logo span{color:var(--primary)}
+ .nav-links{display:flex;gap:20px;margin-left:auto;flex-wrap:wrap}.nav-links a{font-size:.85rem;font-weight:500;color:var(--text-soft)}
+ .nav-btn{padding:7px 16px;background:var(--primary);color:#fff;border-radius:7px;font-size:.83rem;font-weight:600}
+ article{padding:116px 0 80px}
+ h1{font-size:2rem;font-weight:800;line-height:1.3;margin-bottom:14px}
+ h2{font-size:1.3rem;font-weight:700;margin:38px 0 14px;padding-top:18px;border-top:1px solid var(--border)}
+ p{margin-bottom:14px;color:var(--text-soft)}
+ ol,ul{margin:0 0 16px 22px;color:var(--text-soft)}li{margin-bottom:7px}
+ table{width:100%;border-collapse:collapse;margin:18px 0;font-size:.88rem}
+ th,td{padding:11px 12px;text-align:left;vertical-align:top;border-bottom:1px solid var(--border)}th{font-weight:600;background:var(--surface);color:var(--text)}
+ code{font-family:ui-monospace,Menlo,monospace}p code,li code,td code{background:var(--surface);padding:2px 6px;border-radius:5px;font-size:.85em;color:var(--primary-dark)}
+ .post-meta{color:var(--text-muted);font-size:.85rem;margin-bottom:22px}
+ .lead{font-size:1.05rem;color:var(--text);margin:22px 0}
+ figure{margin:0 0 26px}.hero-media{display:block;width:100%;aspect-ratio:1097/676;object-fit:cover;border-radius:8px;border:1px solid var(--border)}figcaption{font-size:.78rem;color:var(--text-muted);margin-top:8px}
+ .proof{border-left:4px solid var(--accent);background:#f0fdf4;padding:14px 16px;margin:18px 0;color:#14532d}
+ .cta{background:var(--surface);border:1px solid var(--border);border-radius:8px;padding:24px;margin:30px 0;text-align:center}.cta p{margin-bottom:16px}.cta a.btn{display:inline-block;padding:10px 22px;background:var(--primary);color:#fff;border-radius:7px;font-weight:600}
+ footer{background:#0f172a;color:#94a3b8;padding:28px 0;text-align:center;font-size:.8rem}footer a{color:#94a3b8}
+ @media(max-width:900px){.nav-links{display:none}.nav .container{gap:16px}.nav-logo{margin-right:auto}h1{font-size:1.65rem}table{font-size:.8rem}th,td{padding:9px 8px}}
+ </style>
+</head>
+<body>
+<nav class="nav"><div class="container"><a href="/en/" class="nav-logo">Fun<span>ASR</span></a><div class="nav-links"><a href="/en/#capabilities">Capabilities</a><a href="/en/#usage">How to Use</a><a href="/en/#benchmark">Benchmark</a><a href="/en/#demo">Demo</a><a href="https://modelscope.github.io/FunASR/" target="_blank">Docs</a><a href="/en/quickstart.html">Quickstart</a><a href="/en/models.html">Models</a><a href="/en/ecosystem.html">Ecosystem</a><a href="/en/blog/">Blog</a><a href="/en/vs-whisper.html">vs Whisper</a><a href="/en/donors.html">Thanks</a></div><a href="/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html" style="font-size:.83rem;font-weight:500;color:var(--text-soft)">中文</a><a href="https://github.com/modelscope/FunASR" target="_blank" rel="noopener" class="nav-btn">GitHub ★</a></div></nav>
+<article><div class="container">
+ <h1>Subtitle Edit 5.2: Generate Local Video Subtitles with Fun-ASR Nano or SenseVoice</h1>
+ <p class="post-meta">August 3, 2026 · FunASR ecosystem integration</p>
+ <figure>
+ <img class="hero-media" src="/img/subtitle-edit-speech-to-text.png" alt="Subtitle Edit Speech to text workspace for video subtitles">
+ <figcaption>Official Subtitle Edit Speech to text workspace. The screenshot shows the transcription interface; the v5.2.0-beta2 Engine menu also includes Fun-ASR Nano and SenseVoice.</figcaption>
+ </figure>
+ <p class="lead"><a href="https://github.com/SubtitleEdit/subtitleedit" target="_blank" rel="noopener">Subtitle Edit</a> is a cross-platform, open-source subtitle editor. Its <a href="https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2" target="_blank" rel="noopener">v5.2.0-beta2</a> release contains the <code>Crisp ASR Fun-ASR Nano</code> and <code>Crisp ASR SenseVoice</code> local speech engines on Windows, macOS, and Linux. You can generate subtitles from video and keep working in the same app to time, segment, review, and export them.</p>
+ <div class="proof"><strong>Release status:</strong> this is currently a beta release. Validate the workflow with representative video before using it in production. This guide only describes capabilities verified in the exact v5.2.0-beta2 tag.</div>
+
+ <h2>Start local transcription in three steps</h2>
+ <ol>
+ <li>Install or extract Subtitle Edit v5.2.0-beta2 and open the source video.</li>
+ <li>Choose <code>Video → Audio to text</code>.</li>
+ <li>Set Engine to <code>Crisp ASR Fun-ASR Nano</code> or <code>Crisp ASR SenseVoice</code>, then choose a language and model precision and start transcription.</li>
+ </ol>
+ <p>The workflow stays in Subtitle Edit, without sending audio to a cloud service. The resulting subtitles can use its timeline, waveform, format conversion, and quality-control tools.</p>
+
+ <h2>Choose the right backend</h2>
+ <table>
+ <thead><tr><th>Engine</th><th>Languages</th><th>Precision and download size</th><th>Best fit</th></tr></thead>
+ <tbody>
+ <tr><td><a href="/go/fun-asr">Fun-ASR Nano</a></td><td>Chinese, Cantonese, English, Japanese, Korean</td><td>Q4 0.90 GB<br>Q8 1.27 GB<br>F16 1.98 GB</td><td>Stronger transcription with enough device memory</td></tr>
+ <tr><td><a href="/go/sensevoice">SenseVoice</a></td><td>Auto detection, Chinese, Cantonese, English, Japanese, Korean</td><td>Q4 136 MB<br>Q8 252 MB<br>F16 469 MB</td><td>A compact runtime with native language, emotion, and audio-event tags</td></tr>
+ </tbody>
+ </table>
+ <p>The language lists and model sizes come directly from the v5.2.0-beta2 <a href="https://github.com/SubtitleEdit/subtitleedit/blob/v5.2.0-beta2/src/ui/Features/Video/SpeechToText/Engines/CrispAsrFunAsrNano.cs" target="_blank" rel="noopener">Fun-ASR Nano engine source</a> and <a href="https://github.com/SubtitleEdit/subtitleedit/blob/v5.2.0-beta2/src/ui/Features/Video/SpeechToText/Engines/CrispAsrSenseVoice.cs" target="_blank" rel="noopener">SenseVoice engine source</a>. Q4 minimizes memory use, Q8 balances size and precision, and F16 is the largest option.</p>
+
+ <h2>What this beta update verifies</h2>
+ <p><a href="https://github.com/SubtitleEdit/subtitleedit/pull/13063" target="_blank" rel="noopener">Subtitle Edit PR #13063</a> updates the CrispASR runtime and reports a SenseVoice transcription probe on the Apple Metal path. It also adds other engines. Fun-ASR Nano and SenseVoice were already present in the project, so this is not presented as the PR that first introduced those backends.</p>
+ <ul>
+ <li>The release supplies downloadable assets for Windows, macOS, and Linux.</li>
+ <li>All three precision options for Fun-ASR Nano and SenseVoice are listed in the exact-tag source.</li>
+ <li>The local workflow keeps recognition, subtitle timing, segmentation, and format export in one desktop tool.</li>
+ </ul>
+
+ <div class="cta">
+ <p>Validate timing and text quality on a short representative clip before processing long video. For reproducible reports, include the operating system, engine, model precision, and a minimal media sample.</p>
+ <a class="btn" href="https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2" target="_blank" rel="noopener">Download Subtitle Edit v5.2.0-beta2</a>
+ </div>
+</div></article>
+<footer><div class="container">© 2024-2026 Tongyi Lab, Alibaba Group · <a href="https://github.com/modelscope/FunASR/blob/main/LICENSE">MIT License</a></div></footer>
+</body>
+</html>
diff --git a/web-pages/product-site/legacy/en/ecosystem.html b/web-pages/product-site/legacy/en/ecosystem.html
index d069654f0..42ea10840 100644
--- a/web-pages/product-site/legacy/en/ecosystem.html
+++ b/web-pages/product-site/legacy/en/ecosystem.html
@@ -61,11 +61,11 @@ pre{background:#1e293b;color:#e2e8f0;padding:18px;border-radius:10px;overflow-x:
.cta a.btn.outline{background:transparent;color:var(--primary);border:1px solid var(--primary)}
footer{background:#0f172a;color:#94a3b8;padding:32px 0;font-size:0.82rem;text-align:center;margin-top:60px}
footer a{color:#60a5fa}
-@media(max-width:640px){h1{font-size:1.5rem}.stat-bar{gap:20px}.stat-num{font-size:1.5rem}.card-grid{grid-template-columns:1fr}}
+@media(max-width:640px){.nav-links{display:none}.nav-logo{margin-right:auto}h1{font-size:1.5rem}.stat-bar{gap:20px}.stat-num{font-size:1.5rem}.card-grid{grid-template-columns:1fr}}
</style>
</head>
<body>
-<nav class="nav"><div class="container"><a class="nav-logo" href="../en/">Fun<span>ASR</span></a><div class="nav-links"><a href="/en/#capabilities">Capabilities</a><a href="/en/#usage">How to Use</a><a href="/en/#benchmark">Benchmark</a><a href="/en/#demo">Demo</a><a href="https://modelscope.github.io/FunASR/" target="_blank">Docs</a><a href="quickstart.html">Quickstart</a><a href="models.html">Models</a><a href="ecosystem.html">Ecosystem</a><a href="/en/blog/">Blog</a><a href="vs-whisper.html">vs Whisper</a><a href="/en/donors.html">Thanks</a><a href="/ecosystem.html" style="font-size:0.85rem;font-weight:500;color:var(--text-soft);text-decoration:none">中文</a><a href="https://github.com/modelscope/FunASR" target="_blank" class="nav-btn">GitHub ★</a></div></div></nav>
+<nav class="nav"><div class="container"><a class="nav-logo" href="../en/">Fun<span>ASR</span></a><div class="nav-links"><a href="/en/#capabilities">Capabilities</a><a href="/en/#usage">How to Use</a><a href="/en/#benchmark">Benchmark</a><a href="/en/#demo">Demo</a><a href="https://modelscope.github.io/FunASR/" target="_blank">Docs</a><a href="quickstart.html">Quickstart</a><a href="models.html">Models</a><a href="ecosystem.html">Ecosystem</a><a href="/en/blog/">Blog</a><a href="vs-whisper.html">vs Whisper</a><a href="/en/donors.html">Thanks</a></div><a href="/ecosystem.html" style="font-size:0.85rem;font-weight:500;color:var(--text-soft);text-decoration:none">中文</a><a href="https://github.com/modelscope/FunASR" target="_blank" class="nav-btn">GitHub ★</a></div></nav>
<article>
<div class="container">
@@ -95,6 +95,12 @@ footer a{color:#60a5fa}
<div><span class="card-tag">Live Transcription</span><span class="card-tag">SenseVoiceSmall</span></div>
</div>
<div class="card">
+<div class="card-title"><a href="https://github.com/SubtitleEdit/subtitleedit">Subtitle Edit</a></div>
+<div class="card-stars">13.7K+ stars</div>
+<div class="card-desc"><a href="https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2">v5.2.0-beta2</a> ships local Fun-ASR Nano and SenseVoice video subtitle engines for Windows, macOS, and Linux, with Q4, Q8, and F16 models. <a href="https://github.com/SubtitleEdit/subtitleedit/pull/13063">PR #13063</a> updates the CrispASR runtime and verifies the SenseVoice Metal path; <a href="/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html">read the setup and model guide</a>.</div>
+<div><span class="card-tag">Video Subtitles</span><span class="card-tag">Fun-ASR Nano</span><span class="card-tag">SenseVoice</span></div>
+</div>
+<div class="card">
<div class="card-title"><a href="https://github.com/jianchang512/pyvideotrans">pyVideoTrans</a></div>
<div class="card-stars">17.6K stars</div>
<div class="card-desc">Video translation tool. Uses FunASR for Chinese speech recognition with subtitle generation.</div>
diff --git a/web-pages/product-site/legacy/img/subtitle-edit-speech-to-text.png b/web-pages/product-site/legacy/img/subtitle-edit-speech-to-text.png
new file mode 100644
index 000000000..d804a7185
Binary files /dev/null and b/web-pages/product-site/legacy/img/subtitle-edit-speech-to-text.png differ
diff --git a/web-pages/product-site/tests/test_output.py b/web-pages/product-site/tests/test_output.py
index 0463b61e4..2d463b4d3 100644
--- a/web-pages/product-site/tests/test_output.py
+++ b/web-pages/product-site/tests/test_output.py
@@ -196,6 +196,110 @@ def test_ecosystem_surfaces_merged_whisperlivekit_sensevoice_backend(
assert marker in text
[email protected]('relative', ('ecosystem.html', 'en/ecosystem.html'))
+def test_ecosystem_surfaces_released_subtitle_edit_funasr_backends(
+ built_site, relative
+):
+ soup = read_soup(built_site / relative)
+ anchor = soup.select_one(
+ '.card-title a[href="https://github.com/SubtitleEdit/subtitleedit"]'
+ )
+
+ assert anchor
+ card = anchor.find_parent(class_='card')
+ assert card
+ links = {link.get('href') for link in card.select('a[href]')}
+ assert {
+ 'https://github.com/SubtitleEdit/subtitleedit/pull/13063',
+ 'https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2',
+ } <= links
+ text = card.get_text(' ', strip=True)
+ for marker in (
+ '13.7K',
+ 'Fun-ASR Nano',
+ 'SenseVoice',
+ 'Q4',
+ 'Q8',
+ 'F16',
+ 'Windows',
+ 'macOS',
+ 'Linux',
+ 'v5.2.0-beta2',
+ ):
+ assert marker in text
+
+
+ ('relative', 'peer', 'markers'),
+ (
+ (
+ 'blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html',
+ '/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html',
+ ('视频', '字幕', '当前是 beta 版本'),
+ ),
+ (
+ 'en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html',
+ '/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html',
+ ('video', 'subtitles', 'currently a beta release'),
+ ),
+ ),
+)
+def test_subtitle_edit_blog_is_bilingual_and_evidence_backed(
+ built_site, relative, peer, markers
+):
+ page = built_site / relative
+ soup = read_soup(page)
+ text = soup.get_text(' ', strip=True)
+
+ assert soup.select_one('link[rel="canonical"]')['href'].endswith('/' + relative)
+ assert soup.select_one(f'link[rel="alternate"][href$="{peer}"]')
+ image = soup.select_one('article img[src]')
+ assert image
+ assert (built_site / image['src'].lstrip('/')).is_file()
+ links = {link.get('href') for link in soup.select('a[href]')}
+ assert {
+ 'https://github.com/SubtitleEdit/subtitleedit',
+ 'https://github.com/SubtitleEdit/subtitleedit/pull/13063',
+ 'https://github.com/SubtitleEdit/subtitleedit/releases/tag/v5.2.0-beta2',
+ '/go/fun-asr',
+ '/go/sensevoice',
+ } <= links
+ for marker in (
+ 'Video',
+ 'Audio to text',
+ 'Crisp ASR Fun-ASR Nano',
+ 'Crisp ASR SenseVoice',
+ 'Q4',
+ 'Q8',
+ 'F16',
+ 'Windows',
+ 'macOS',
+ 'Linux',
+ 'v5.2.0-beta2',
+ *markers,
+ ):
+ assert marker in text
+
+
+ ('relative', 'href'),
+ (
+ (
+ 'blog/index.html',
+ '/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html',
+ ),
+ (
+ 'en/blog/index.html',
+ '/en/blog/subtitle-edit-fun-asr-sensevoice-local-subtitles.html',
+ ),
+ ),
+)
+def test_blog_indexes_surface_subtitle_edit_release(built_site, relative, href):
+ soup = read_soup(built_site / relative)
+
+ assert soup.select_one(f'a[href="{href}"]')
+
+
def test_complete_build_passes_output_validation(built_site):
assert validate_output(built_site) == []