FunASR/docs/community_projects.md

English | 简体中文

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
Pipecat	A local FunASRSTTService backed by SenseVoice for voice and multimodal agent pipelines, with transcription and voice-agent examples.	FunASR service docs, transcription example, voice-agent example, and merged #4844.
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, configuration, and merged #3255.
AutoSubs	An on-device int8 ONNX SenseVoice engine for subtitle generation in DaVinci Resolve, Premiere, and After Effects.	SenseVoice model notes, engine source, and merged #629.
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, recognizer source, and merged #110.
OmniVoice Studio	Its OpenAI-compatible remote ASR backend can point dictation and dubbing workflows at a self-hosted FunASR or SenseVoice server.	OpenAI-compatible ASR guide and merged #1003.
GPT-SoVITS	Dataset preparation and WebUI transcription with Fun-ASR-Nano, SenseVoice, and classic FunASR models.	funasr_asr.py, runtime fallback #2801, and backend documentation #2803.
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, FunASR service, and merged #65.

Model serving and runtimes

Project	What is integrated	Start here
Xinference	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 and the FunASR 1.3 compatibility update in merged #5140.
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 and the deterministic ASR decoding fix in merged #20.
vad-burn	FSMN VAD inference in pure Rust with Python bindings, including offline, streaming, and CPU-only modes.	Project README and the FunASR showcase in #3106.

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.

Add your project

If you maintain a FunASR integration, open a showcase issue 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