[English](./community_projects.md) | [简体中文](./community_projects_zh.md)

# FunASR Community Integrations

This page lists maintained projects where FunASR, Fun-ASR-Nano, SenseVoice, or an official FunASR model is already integrated upstream. Each entry below was checked against the project's default branch and, where available, a linked merged change.

These integrations are community-maintained. Their release cadence, hardware support, and API stability are controlled by the upstream project, not by the FunASR maintainers.

## Voice agents and applications

| Project | What is integrated | Start here |
|---|---|---|
| [recording-inbox](https://github.com/chenmozhe008/recording-inbox) | A self-hosted Feishu/Lark recording inbox that runs SenseVoiceSmall locally on macOS or Windows, then publishes structured meeting minutes and a timestamped transcript back to Feishu. The resumable pipeline has been exercised on multi-hour recordings, with a real CPU-only inference check and cross-platform mocked CI. | [Project guide](https://chenmozhe008.github.io/recording-inbox/), [macOS setup](https://github.com/chenmozhe008/recording-inbox/blob/master/docs/setup-macos.md), and FunASR showcase [#3294](https://github.com/modelscope/FunASR/issues/3294). |
| [Pipecat](https://github.com/pipecat-ai/pipecat) | A local `FunASRSTTService` backed by SenseVoice for voice and multimodal agent pipelines, with transcription and voice-agent examples. | [FunASR service docs](https://docs.pipecat.ai/api-reference/server/services/stt/funasr), [transcription example](https://github.com/pipecat-ai/pipecat/blob/main/examples/transcription/transcription-funasr.py), [voice-agent example](https://github.com/pipecat-ai/pipecat/blob/main/examples/voice/voice-funasr.py), and merged [#4844](https://github.com/pipecat-ai/pipecat/pull/4844). |
| [xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) | The default local ASR provider uses FunASR with SenseVoiceSmall; recognition language can be set to `auto`, `zh`, `en`, `ja`, `ko`, or `yue`. A separate FunASR runtime-server provider is also available. | [Provider implementation](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/main/xiaozhi-server/core/providers/asr/fun_local.py), [configuration](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/main/xiaozhi-server/config.yaml), and merged [#3255](https://github.com/xinnan-tech/xiaozhi-esp32-server/pull/3255). |
| [AutoSubs](https://github.com/tmoroney/auto-subs) | An on-device int8 ONNX SenseVoice engine for subtitle generation in DaVinci Resolve, Premiere, and After Effects. | [SenseVoice model notes](https://github.com/tmoroney/auto-subs#sensevoice), [engine source](https://github.com/tmoroney/auto-subs/blob/main/AutoSubs-App/src-tauri/crates/transcription-engine/src/engines/sense_voice.rs), and merged [#629](https://github.com/tmoroney/auto-subs/pull/629). |
| [TMSpeech](https://github.com/jxlpzqc/TMSpeech) | A Windows meeting subtitle and translation app that can run Fun-ASR-Nano INT8 through its external-command recognizer. Silero VAD completes each utterance before Nano decoding, while the existing low-cost C# streaming recognizer remains available. | [Fun-ASR-Nano setup](https://github.com/jxlpzqc/TMSpeech/blob/master/README.md#%E4%BD%BF%E7%94%A8-fun-asr-nano), [recognizer source](https://github.com/jxlpzqc/TMSpeech/blob/master/external_recognizer/simulate-streaming-funasr-nano.py), and merged [#110](https://github.com/jxlpzqc/TMSpeech/pull/110). |
| [SmartSub](https://github.com/buxuku/SmartSub) | A cross-platform desktop app for local transcription, subtitle translation, dubbing, and video export. Its offline FunASR engine runs SenseVoice and Paraformer through the bundled sherpa-onnx runtime, with in-app model downloads and folder import. | [Project README](https://github.com/buxuku/SmartSub#readme), [FunASR resource panel](https://github.com/buxuku/SmartSub/blob/main/renderer/components/resources/FunasrModelSection.tsx), and merged download-recovery guidance [#392](https://github.com/buxuku/SmartSub/pull/392). |
| [clowder-ai](https://github.com/zts212653/clowder-ai) | A local AI service launcher whose `whisper-stt` slot now includes Qwen3-ASR as a backend model variant, making local ASR setup visible without adding a separate speech service. | [Service manifest](https://github.com/zts212653/clowder-ai/blob/main/packages/cli/src/services/service-manifest.ts), [recommendation matrix](https://github.com/zts212653/clowder-ai/blob/main/packages/cli/src/services/recommendation-matrix.yaml), and merged [#1083](https://github.com/zts212653/clowder-ai/pull/1083). |
| [QuQu](https://github.com/yan5xu/ququ) | A Chinese desktop voice-to-text workflow and open-source Wispr Flow alternative with a local FunASR Paraformer pipeline, bundled `funasr_server.py`, VAD, punctuation restoration, and optional LLM text optimization. | [Project README](https://github.com/yan5xu/ququ#readme), [FunASR server](https://github.com/yan5xu/ququ/blob/main/funasr_server.py), and [package metadata](https://github.com/yan5xu/ququ/blob/main/package.json). |
| [OpenLess](https://github.com/Open-Less/openless) | An open-source macOS and Windows voice input app whose unified Bailian ASR provider exposes Fun-ASR-Flash recorded-file transcription alongside realtime ASR choices for cursor dictation and AI-prompt workflows. | [Project README](https://github.com/Open-Less/openless#readme), [DashScope multimodal ASR provider](https://github.com/Open-Less/openless/blob/beta/openless-all/app/src-tauri/src/asr/dashscope_multimodal.rs), [provider settings copy](https://github.com/Open-Less/openless/blob/beta/openless-all/app/src/i18n/en.ts), and merged [#793](https://github.com/Open-Less/openless/pull/793). |
| [OmniVoice Studio](https://github.com/debpalash/OmniVoice-Studio) | A local voice-cloning, dubbing, dictation, and audiobook app with both an OpenAI-compatible remote ASR backend for self-hosted FunASR/SenseVoice servers and a native FunASR/SenseVoice + CAM++ path that keeps speaker identities consistent across whole recordings. | [OpenAI-compatible ASR guide](https://github.com/debpalash/OmniVoice-Studio/blob/main/docs/engines/openai-compatible-asr.md), [FunASR backend](https://github.com/debpalash/OmniVoice-Studio/blob/main/backend/services/asr_backend.py), merged [#1003](https://github.com/debpalash/OmniVoice-Studio/pull/1003), and merged [#1167](https://github.com/debpalash/OmniVoice-Studio/pull/1167). |
| [GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS) | Dataset preparation and WebUI transcription with Fun-ASR-Nano, SenseVoice, and classic FunASR models. | [`funasr_asr.py`](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/tools/asr/funasr_asr.py), runtime fallback [#2801](https://github.com/RVC-Boss/GPT-SoVITS/pull/2801), and backend documentation [#2803](https://github.com/RVC-Boss/GPT-SoVITS/pull/2803). |
| [AudioNotes](https://github.com/harry0703/AudioNotes) | Audio and video note extraction to structured Markdown with Fun-ASR-MLT-Nano routed through the Fun-ASR Nano inference profile, including cache, batch size, and list-based hotwords. | [Project README](https://github.com/harry0703/AudioNotes#readme), [FunASR service](https://github.com/harry0703/AudioNotes/blob/main/app/services/asr_funasr.py), and merged [#65](https://github.com/harry0703/AudioNotes/pull/65). |
| [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 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). |
| [SayIt](https://github.com/crosswk/SayIt) | A local voice-input assistant with FunASR and SenseVoice ASR modes; the merged hotword clarification documents which modes support FunASR hotwords so users can choose the right backend before recording. | [Project README](https://github.com/crosswk/SayIt#readme), [ASR package](https://github.com/crosswk/SayIt/tree/main/packages/asr), and merged [#23](https://github.com/crosswk/SayIt/pull/23). |
| [VocaLinux](https://github.com/jatinkrmalik/vocalinux) | An offline Linux dictation app whose remote ASR engine can connect to self-hosted FunASR or SenseVoice OpenAI-compatible endpoints. | [Remote ASR guide](https://github.com/jatinkrmalik/vocalinux/blob/main/docs/HTTP_REMOTE.md), [recognition manager](https://github.com/jatinkrmalik/vocalinux/blob/main/src/vocalinux/speech_recognition/recognition_manager.py), and merged [#468](https://github.com/jatinkrmalik/vocalinux/pull/468). |
| [VocoType-linux](https://github.com/LeonardNJU/VocoType-linux) | A Linux desktop dictation workflow whose IBus integration can run a FunASR-backed system Python ASR runtime; the merged validation fix keeps the desktop input path reproducible instead of depending on an interactive shell environment. | [Project README](https://github.com/LeonardNJU/VocoType-linux#readme), [IBus engine](https://github.com/LeonardNJU/VocoType-linux/tree/main/ibus_engine), and merged [#32](https://github.com/LeonardNJU/VocoType-linux/pull/32). |
| [TranscriptionSuite](https://github.com/homelab-00/TranscriptionSuite) | A local private speech-to-text desktop/server app with a SenseVoice/FunASR backend, OpenAI-compatible audio routes, and CAM++ diarization support. | [SenseVoice backend](https://github.com/homelab-00/TranscriptionSuite/blob/main/server/backend/core/stt/backends/sensevoice_backend.py), [OpenAI audio route](https://github.com/homelab-00/TranscriptionSuite/blob/main/server/backend/api/routes/openai_audio.py), merged [#198](https://github.com/homelab-00/TranscriptionSuite/pull/198), and merged [#201](https://github.com/homelab-00/TranscriptionSuite/pull/201). |

## Model serving and runtimes

| Project | What is integrated | Start here |
|---|---|---|
| [Xinference](https://github.com/xorbitsai/inference) | Built-in audio model specifications for SenseVoiceSmall, Fun-ASR-Nano-2512, and Fun-ASR-MLT-Nano-2512 through Xinference's unified inference API. | [Audio model specifications](https://github.com/xorbitsai/inference/blob/main/xinference/model/audio/model_spec.json) and the FunASR 1.3 compatibility update in merged [#5140](https://github.com/xorbitsai/inference/pull/5140). |
| [Optimum Intel](https://github.com/huggingface/optimum-intel) | OpenVINO export and inference support for Fun-ASR models through Hugging Face Optimum Intel, including FunASR-specific modeling and ASR/export/quantization coverage. | [FunASR OpenVINO modeling](https://github.com/huggingface/optimum-intel/blob/main/optimum/intel/openvino/modeling_funasr.py), [supported models docs](https://github.com/huggingface/optimum-intel/blob/main/docs/source/openvino/models.mdx), and merged [#1801](https://github.com/huggingface/optimum-intel/pull/1801). |
| [OpenVINO Notebooks](https://github.com/openvinotoolkit/openvino_notebooks) | Official OpenVINO tutorial material for FunASR-Nano, including helper code and NPU device fixes for running the notebook on Intel acceleration paths. | [FunASR-Nano notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/funasr-nano), [OpenVINO FunASR helper](https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/funasr-nano/ov_funasr_helper.py), merged [#3497](https://github.com/openvinotoolkit/openvino_notebooks/pull/3497), and NPU fix [#3517](https://github.com/openvinotoolkit/openvino_notebooks/pull/3517). |
| [SGLang Omni](https://github.com/sgl-project/sglang-omni) | A multi-stage pipeline runtime for omni models with built-in Fun-ASR model support, OpenAI-compatible serving, cookbook docs, benchmark tasks, and formatted stream-output tests. | [Fun-ASR cookbook](https://github.com/sgl-project/sglang-omni/blob/main/docs/cookbook/fun_asr.md), [Fun-ASR model runtime](https://github.com/sgl-project/sglang-omni/tree/main/sglang_omni/models/fun_asr), merged [#1078](https://github.com/sgl-project/sglang-omni/pull/1078), and merged review-fix [#1079](https://github.com/sgl-project/sglang-omni/pull/1079). |
| [Fun-ASR-vLLM](https://github.com/yuekaizhang/Fun-ASR-vllm) | Community vLLM inference for Fun-ASR-Nano and Fun-ASR-MLT-Nano, including batch evaluation and NVIDIA Triton deployment. | [Setup and benchmarks](https://github.com/yuekaizhang/Fun-ASR-vllm#readme) and the deterministic ASR decoding fix in merged [#20](https://github.com/yuekaizhang/Fun-ASR-vllm/pull/20). |
| [vad-burn](https://github.com/di-osc/vad-burn) | FSMN VAD inference in pure Rust with Python bindings, including offline, streaming, and CPU-only modes. | [Project README](https://github.com/di-osc/vad-burn#readme) and the FunASR showcase in [#3106](https://github.com/modelscope/FunASR/issues/3106). |

## Discovery lists

| Project | What is integrated | Start here |
|---|---|---|
| [awesome-python](https://github.com/vinta/awesome-python) | SenseVoice is listed in the Speech Recognition section of one of the largest Python resource directories, making it easier for Python developers to discover local multilingual ASR. | [Project README](https://github.com/vinta/awesome-python#readme) and merged [#3246](https://github.com/vinta/awesome-python/pull/3246). |
| [speech-trident](https://github.com/ga642381/speech-trident) | SenseVoice is listed among speech/audio language models in a curated speech LLM, representation learning, and codec model directory. | [Project README](https://github.com/ga642381/speech-trident#readme) and merged [#31](https://github.com/ga642381/speech-trident/pull/31). |
| [voiceai](https://github.com/mahimairaja/voiceai) | A voice-AI agent resource map that lists FunASR and SenseVoice in its Speech-to-text (STT / ASR) section, pointing agent builders toward self-hosted local ASR and multilingual speech understanding options. | [English README](https://github.com/mahimairaja/voiceai#readme), [Chinese README](https://github.com/mahimairaja/voiceai/blob/main/README_zh.md), and merged [#16](https://github.com/mahimairaja/voiceai/pull/16). |
| [Large-Audio-Models](https://github.com/liusongxiang/Large-Audio-Models) | An audio-domain foundation-model directory that lists the FunAudioLLM voice understanding and generation paper with SenseVoice code, helping speech, singing, and music model readers discover the project. | [Project README](https://github.com/liusongxiang/Large-Audio-Models#readme) and merged [#26](https://github.com/liusongxiang/Large-Audio-Models/pull/26). |
| [Neural-Codec-and-Speech-Language-Models](https://github.com/LqNoob/Neural-Codec-and-Speech-Language-Models) | A neural codec, TTS, and speech-language-model directory that lists both Fun-ASR-Nano and SenseVoice for readers comparing ASR and speech-understanding models. | [Project README](https://github.com/LqNoob/Neural-Codec-and-Speech-Language-Models#readme) and merged [#4](https://github.com/LqNoob/Neural-Codec-and-Speech-Language-Models/pull/4). |
| [awesome-LLM-resources](https://github.com/WangRongsheng/awesome-LLM-resources) | A Chinese LLM resource directory that lists FunASR and SenseVoice in its STT / ASR resources, giving multimodal and speech-tool readers another maintained discovery path. | [Project README](https://github.com/WangRongsheng/awesome-LLM-resources#readme) and merged [#162](https://github.com/WangRongsheng/awesome-LLM-resources/pull/162). |

## Before adopting an integration

- Follow the upstream project's installation and release notes; do not assume its dependency versions match FunASR `main`.
- Validate the exact model, language, audio format, and hardware path you plan to deploy.
- Report application or adapter bugs to the integration project. Report reproducible core FunASR model or runtime bugs to [FunASR issues](https://github.com/modelscope/FunASR/issues).

## Add your project

If you maintain a FunASR integration, open a [showcase issue](https://github.com/modelscope/FunASR/issues/new?template=showcase.md) with:

- repository link and maintenance status
- supported FunASR model or runtime path
- install and minimal usage instructions
- a merged change, release, benchmark, or other reproducible validation
- a note about whether the project is official, community-maintained, or experimental