Skip to content

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

docs: surface official Dify Marketplace plugin (#3411)

zhifu gaoa7a5b9408b66
diff --git a/docs/community_projects.md b/docs/community_projects.md
index bb159b83e..1824ec5a4 100644
--- a/docs/community_projects.md
+++ b/docs/community_projects.md
@@ -25,7 +25,7 @@ These integrations are community-maintained. Their release cadence, hardware sup
| [Stet](https://github.com/DengNaichen/Stet) | A macOS local dictation app with an in-process Fun-ASR Nano engine, a universal static runtime derived from FunASR's `llama.cpp` path, Settings-managed encoder/decoder/VAD downloads, runtime reuse, and hotword support from the personal dictionary. | [FunASR package notes](https://github.com/DengNaichen/Stet/blob/main/Packages/StetEngine/Vendor/FunASRPackage/README.md), [Fun-ASR Nano spec](https://github.com/DengNaichen/Stet/blob/main/specs/009-fun-asr-nano/spec.md), and merged release [#44](https://github.com/DengNaichen/Stet/pull/44). |
| [NarratoAI](https://github.com/linyqh/NarratoAI) | An AI video narration and editing app whose OpenAI-compatible transcription endpoint can point subtitle generation at a self-hosted FunASR service. | [FunASR subtitle service](https://github.com/linyqh/NarratoAI/blob/main/app/services/fun_asr_subtitle.py), [configuration example](https://github.com/linyqh/NarratoAI/blob/main/config.example.toml), and merged [#259](https://github.com/linyqh/NarratoAI/pull/259). |
| [wyoming-faster-whisper](https://github.com/OHF-Voice/wyoming-faster-whisper) | A Wyoming protocol speech-to-text server with an optional FunASR backend, making SenseVoice/FunASR available to local voice-assistant deployments that speak Wyoming. | [FunASR handler](https://github.com/OHF-Voice/wyoming-faster-whisper/blob/master/wyoming_faster_whisper/funasr_handler.py), [model registry](https://github.com/OHF-Voice/wyoming-faster-whisper/blob/master/wyoming_faster_whisper/models.py), and merged [#95](https://github.com/OHF-Voice/wyoming-faster-whisper/pull/95). |
-| [Dify official plugins](https://github.com/langgenius/dify-official-plugins) | An official Dify speech-to-text model provider for self-hosted FunASR endpoints, with presets for SenseVoice, Fun-ASR-Nano, Paraformer, and Paraformer English. | [FunASR plugin README](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/README.md), [provider implementation](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/provider/funasr.py), [speech-to-text adapter](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/models/speech2text/speech2text.py), and merged [#3281](https://github.com/langgenius/dify-official-plugins/pull/3281). |
+| [Dify FunASR plugin](https://marketplace.dify.ai/plugin/langgenius/funasr) | The official Dify speech-to-text model provider for self-hosted FunASR endpoints. Marketplace version 0.1.1 includes SenseVoice, Fun-ASR-Nano, Paraformer, and Paraformer English presets with a 25 MB upload limit. | [Official plugin source](https://github.com/langgenius/dify-official-plugins/tree/main/models/funasr), [provider implementation](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/provider/funasr.py), initial integration [#3281](https://github.com/langgenius/dify-official-plugins/pull/3281), and 0.1.1 release update [#3498](https://github.com/langgenius/dify-official-plugins/pull/3498). |
| [RAGFlow](https://github.com/infiniflow/ragflow) | A Retrieval-Augmented Generation and agent platform with a local FunASR / SenseVoice speech-to-text provider for self-hosted document and media ingestion workflows, plus hosted Fun-ASR-Flash speech-to-text through the Tongyi-Qianwen provider. | [Provider registration](https://github.com/infiniflow/ragflow/blob/main/rag/llm/sequence2txt_model.py), [supported models docs](https://github.com/infiniflow/ragflow/blob/main/docs/guides/models/supported_models.mdx), merged [#16473](https://github.com/infiniflow/ragflow/pull/16473), and merged [#16844](https://github.com/infiniflow/ragflow/pull/16844). |
| [LiveTalking](https://github.com/lipku/LiveTalking) | A real-time interactive digital-human server with a local FunASR/SenseVoice ASR server path; the merged fix serializes shared model access so concurrent requests do not race during lazy model loading or `generate()`. | [ASR server](https://github.com/lipku/LiveTalking/blob/main/server/asr_server.py), [project README](https://github.com/lipku/LiveTalking#readme), and merged [#611](https://github.com/lipku/LiveTalking/pull/611). |
| [Sokuji](https://github.com/kizuna-ai-lab/sokuji) | A live speech translation app whose local inference sidecar supports GPU-native SenseVoice through FunASR plus built-in offline Fun-ASR-Nano and Fun-ASR-MLT-Nano catalog cards for CPU/GPU ASR. | [Sidecar model catalog](https://github.com/kizuna-ai-lab/sokuji/blob/main/sidecar/sokuji_sidecar/catalog.py), [native model catalog](https://github.com/kizuna-ai-lab/sokuji/blob/main/src/lib/local-inference/native/nativeCatalog.ts), merged [#268](https://github.com/kizuna-ai-lab/sokuji/pull/268), merged [#270](https://github.com/kizuna-ai-lab/sokuji/pull/270), and merged [#329](https://github.com/kizuna-ai-lab/sokuji/pull/329). |
diff --git a/docs/community_projects_zh.md b/docs/community_projects_zh.md
index 4da91803b..9d230423e 100644
--- a/docs/community_projects_zh.md
+++ b/docs/community_projects_zh.md
@@ -25,7 +25,7 @@
| [Stet](https://github.com/DengNaichen/Stet) | macOS 本地听写应用,内置 in-process Fun-ASR Nano 引擎;其 universal static runtime 源自 FunASR `llama.cpp` 路径,并通过 Settings 管理 encoder、decoder、VAD 下载,支持 runtime 复用和个人词典 hotwords。 | [FunASR package 说明](https://github.com/DengNaichen/Stet/blob/main/Packages/StetEngine/Vendor/FunASRPackage/README.md)、[Fun-ASR Nano spec](https://github.com/DengNaichen/Stet/blob/main/specs/009-fun-asr-nano/spec.md) 和已合并 release [#44](https://github.com/DengNaichen/Stet/pull/44)。 |
| [NarratoAI](https://github.com/linyqh/NarratoAI) | AI 视频解说与剪辑应用,可通过 OpenAI 兼容转写 endpoint,把字幕生成连接到自托管 FunASR 服务。 | [FunASR 字幕服务](https://github.com/linyqh/NarratoAI/blob/main/app/services/fun_asr_subtitle.py)、[配置示例](https://github.com/linyqh/NarratoAI/blob/main/config.example.toml) 和已合并 [#259](https://github.com/linyqh/NarratoAI/pull/259)。 |
| [wyoming-faster-whisper](https://github.com/OHF-Voice/wyoming-faster-whisper) | Wyoming 协议 speech-to-text server,提供可选 FunASR backend,让本地语音助手和 Home Assistant 相关部署可以通过 Wyoming 使用 SenseVoice/FunASR。 | [FunASR handler](https://github.com/OHF-Voice/wyoming-faster-whisper/blob/master/wyoming_faster_whisper/funasr_handler.py)、[模型注册](https://github.com/OHF-Voice/wyoming-faster-whisper/blob/master/wyoming_faster_whisper/models.py) 和已合并 [#95](https://github.com/OHF-Voice/wyoming-faster-whisper/pull/95)。 |
-| [Dify official plugins](https://github.com/langgenius/dify-official-plugins) | 面向自托管 FunASR endpoint 的 Dify 官方 speech-to-text 模型 provider,内置 SenseVoice、Fun-ASR-Nano、Paraformer 和 Paraformer English 配置。 | [FunASR 插件 README](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/README.md)、[provider 实现](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/provider/funasr.py)、[speech-to-text adapter](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/models/speech2text/speech2text.py) 和已合并 [#3281](https://github.com/langgenius/dify-official-plugins/pull/3281)。 |
+| [Dify FunASR 插件](https://marketplace.dify.ai/plugin/langgenius/funasr) | 面向自托管 FunASR endpoint 的 Dify 官方 speech-to-text 模型 provider。Marketplace 0.1.1 内置 SenseVoice、Fun-ASR-Nano、Paraformer 和 Paraformer English 配置,上传上限为 25 MB。 | [官方插件源码](https://github.com/langgenius/dify-official-plugins/tree/main/models/funasr)、[provider 实现](https://github.com/langgenius/dify-official-plugins/blob/main/models/funasr/provider/funasr.py)、初始集成 [#3281](https://github.com/langgenius/dify-official-plugins/pull/3281) 和 0.1.1 发布更新 [#3498](https://github.com/langgenius/dify-official-plugins/pull/3498)。 |
| [RAGFlow](https://github.com/infiniflow/ragflow) | RAG 与 Agent 平台,提供本地 FunASR / SenseVoice speech-to-text provider,适合自托管文档和媒体摄取工作流;同时可通过 Tongyi-Qianwen provider 使用托管 Fun-ASR-Flash speech-to-text。 | [Provider 注册](https://github.com/infiniflow/ragflow/blob/main/rag/llm/sequence2txt_model.py)、[支持模型文档](https://github.com/infiniflow/ragflow/blob/main/docs/guides/models/supported_models.mdx)、已合并 [#16473](https://github.com/infiniflow/ragflow/pull/16473) 和已合并 [#16844](https://github.com/infiniflow/ragflow/pull/16844)。 |
| [LiveTalking](https://github.com/lipku/LiveTalking) | 实时交互数字人服务,包含本地 FunASR/SenseVoice ASR server 路径;已合并修复会串行化共享模型访问,避免并发请求在懒加载模型或 `generate()` 时竞争。 | [ASR server](https://github.com/lipku/LiveTalking/blob/main/server/asr_server.py)、[项目 README](https://github.com/lipku/LiveTalking#readme) 和已合并 [#611](https://github.com/lipku/LiveTalking/pull/611)。 |
| [Sokuji](https://github.com/kizuna-ai-lab/sokuji) | 实时语音翻译应用,本地推理 sidecar 支持通过 FunASR 使用 GPU-native SenseVoice,并在内置模型目录中提供离线 CPU/GPU Fun-ASR-Nano 与 Fun-ASR-MLT-Nano ASR。 | [Sidecar 模型目录](https://github.com/kizuna-ai-lab/sokuji/blob/main/sidecar/sokuji_sidecar/catalog.py)、[native model catalog](https://github.com/kizuna-ai-lab/sokuji/blob/main/src/lib/local-inference/native/nativeCatalog.ts)、已合并 [#268](https://github.com/kizuna-ai-lab/sokuji/pull/268)、已合并 [#270](https://github.com/kizuna-ai-lab/sokuji/pull/270) 和已合并 [#329](https://github.com/kizuna-ai-lab/sokuji/pull/329)。 |
diff --git a/scripts/check_funasr_website_static.py b/scripts/check_funasr_website_static.py
index db08eb763..97a85b609 100755
--- a/scripts/check_funasr_website_static.py
+++ b/scripts/check_funasr_website_static.py
@@ -20,6 +20,7 @@ class PageContract:
required: tuple[str, ...]
forbidden: tuple[str, ...] = ()
visible_required: tuple[str, ...] = ()
+ visible_patterns: tuple[tuple[str, str], ...] = ()
required_links: tuple[str, ...] = ()
@@ -54,6 +55,13 @@ PAGE_CONTRACTS: dict[str, PageContract] = {
"custom_openai",
"54.3K stars",
),
+ visible_patterns=(
+ ("FunASR 官方插件 0.1.1", r"FunASR 官方插件 0\.1\.1(?![\w.+-])"),
+ ("最大 25 MB 音频上传", r"最大 (?<!\d)25 MB 音频上传"),
+ ),
+ required_links=(
+ "https://marketplace.dify.ai/plugin/langgenius/funasr",
+ ),
forbidden=("16K+",),
),
f"{BASE_URL}/en/ecosystem.html": PageContract(
@@ -64,6 +72,13 @@ PAGE_CONTRACTS: dict[str, PageContract] = {
"custom_openai",
"54.3K stars",
),
+ visible_patterns=(
+ ("FunASR plugin 0.1.1", r"FunASR plugin 0\.1\.1(?![\w.+-])"),
+ ("25 MB uploads", r"(?<!\d)25 MB uploads"),
+ ),
+ required_links=(
+ "https://marketplace.dify.ai/plugin/langgenius/funasr",
+ ),
forbidden=("16K+",),
),
f"{BASE_URL}/donors.html": PageContract(
@@ -314,11 +329,17 @@ def validate_pages(pages: dict[str, str]) -> list[str]:
for needle in contract.required:
if needle not in text:
failures.append(f"{url}: missing `{needle}`")
- if contract.visible_required:
+ visible_text = ""
+ if contract.visible_required or contract.visible_patterns:
visible_text = extract_visible_text(text)
+ if contract.visible_required:
for needle in contract.visible_required:
if needle not in visible_text:
failures.append(f"{url}: visible text missing `{needle}`")
+ if contract.visible_patterns:
+ for label, pattern in contract.visible_patterns:
+ if re.search(pattern, visible_text) is None:
+ failures.append(f"{url}: visible text missing `{label}`")
if contract.required_links:
links = extract_links(text)
for target in contract.required_links:
diff --git a/tests/test_check_funasr_website_static.py b/tests/test_check_funasr_website_static.py
index ae19387d7..125797a93 100644
--- a/tests/test_check_funasr_website_static.py
+++ b/tests/test_check_funasr_website_static.py
@@ -38,6 +38,10 @@ def test_website_contract_accepts_current_public_copy():
<a href="https://github.com/BerriAI/litellm">LiteLLM</a>
<div>custom_openai</div>
<div>54.3K stars</div>
+ <a href="https://marketplace.dify.ai/plugin/langgenius/funasr">
+ FunASR 官方插件 0.1.1
+ </a>
+ <div>支持最大 25 MB 音频上传</div>
""",
"https://www.funasr.com/en/ecosystem.html": """
<div class="stat-num">35K+</div>
@@ -45,6 +49,10 @@ def test_website_contract_accepts_current_public_copy():
<a href="https://github.com/BerriAI/litellm">LiteLLM</a>
<div>custom_openai</div>
<div>54.3K stars</div>
+ <a href="https://marketplace.dify.ai/plugin/langgenius/funasr">
+ FunASR plugin 0.1.1
+ </a>
+ <div>supports 25 MB uploads</div>
""",
"https://www.funasr.com/donors.html": """
捐赠资金用于社区基础设施建设,包括购买和维护服务器,以及购买、续费和维护
@@ -193,6 +201,96 @@ def test_website_contract_includes_homepage_entrypoints():
assert "https://www.funasr.com/en/llama-cpp.html" in checker.PAGE_CONTRACTS
+def test_ecosystem_contract_requires_live_dify_marketplace():
+ checker = _load_module()
+ url = "https://www.funasr.com/en/ecosystem.html"
+ pages = {
+ url: """
+ <body>
+ <div class="stat-num">35K+</div>
+ <a href="/en/donors.html">Thanks</a>
+ <a href="https://github.com/BerriAI/litellm">LiteLLM</a>
+ <div>custom_openai</div>
+ <div>54.3K stars</div>
+ <a href="https://github.com/langgenius/dify">Dify</a>
+ </body>
+ """
+ }
+
+ failures = checker.validate_pages(pages)
+
+ assert any(
+ url in failure
+ and "missing link `https://marketplace.dify.ai/plugin/langgenius/funasr`"
+ in failure
+ for failure in failures
+ )
+ assert any(
+ url in failure and "visible text missing `FunASR plugin 0.1.1`" in failure
+ for failure in failures
+ )
+ assert any(
+ url in failure and "visible text missing `25 MB uploads`" in failure
+ for failure in failures
+ )
+
+
+def _valid_english_ecosystem_html():
+ return """
+ <body>
+ <div class="stat-num">35K+</div>
+ <a href="/en/donors.html">Thanks</a>
+ <a href="https://github.com/BerriAI/litellm">LiteLLM</a>
+ <div>custom_openai</div>
+ <div>54.3K stars</div>
+ <a href="https://marketplace.dify.ai/plugin/langgenius/funasr">
+ FunASR plugin 0.1.1
+ </a>
+ <div>supports 25 MB uploads</div>
+ </body>
+ """
+
+
+def test_ecosystem_contract_rejects_longer_dify_version():
+ checker = _load_module()
+ url = "https://www.funasr.com/en/ecosystem.html"
+ pages = {url: _valid_english_ecosystem_html()}
+ pages[url] = pages[url].replace(
+ "FunASR plugin 0.1.1", "FunASR plugin 0.1.10"
+ )
+
+ failures = checker.validate_pages(pages)
+
+ assert any(url in failure and "FunASR plugin 0.1.1" in failure for failure in failures)
+
+
+def test_ecosystem_contract_rejects_dify_version_suffixes():
+ checker = _load_module()
+ url = "https://www.funasr.com/en/ecosystem.html"
+
+ for version in ("0.1.1-beta", "0.1.1+build"):
+ pages = {url: _valid_english_ecosystem_html()}
+ pages[url] = pages[url].replace("0.1.1", version)
+
+ failures = checker.validate_pages(pages)
+
+ assert any(
+ url in failure and "FunASR plugin 0.1.1" in failure
+ for failure in failures
+ )
+
+
+def test_ecosystem_contract_rejects_larger_dify_upload_limit():
+ checker = _load_module()
+ url = "https://www.funasr.com/en/ecosystem.html"
+ pages = {url: _valid_english_ecosystem_html()}
+ pages[url] = pages[url].replace("25 MB uploads", "125 MB uploads")
+
+ failures = checker.validate_pages(pages)
+
+ assert any(url in failure and "25 MB uploads" in failure for failure in failures)
+
+
def test_website_contract_includes_v1326_launch_articles():
checker = _load_module()