# Fun-ASR-Nano-API

Fun-ASR-Nano-API is a self-hosted ai app. OpenAI-compatible Speech-to-Text API powered by Alibaba FunAudioLLM's Fun-ASR-Nano (800M parameters), supporting 31 languages, Chinese dialects, hotword boosting, VAD, and streaming transcription. It is open source and self-hosted, installable on Unraid.

Canonical page: https://ourlocalhost.com/app/2838/fun-asr-nano-api

## Description

OpenAI-compatible Speech-to-Text API powered by Alibaba FunAudioLLM's Fun-ASR-Nano (800M parameters), supporting 31 languages, Chinese dialects, hotword boosting, VAD, and streaming transcription. For self-hosted audio-to-text pipelines with switchable model support via MODEL_ID. Requires an NVIDIA GPU with driver 550+.

## Platform availability

Available on 1 of 10 platforms: Unraid.

## Health score

38/100 (Low), based on 3 of 4 factors.
- Maintained: 59 (last commit 163 days ago)
- Popular: 6 (1 GitHub stars)
- Easy to install: 35 (1 install platform, install notes, Docker image)

## Links

- Unraid: https://ca.unraid.net/apps/fun-asr-nano-api-0te4gmz0lzb79r?q=Fun-ASR-Nano-API

## Common questions

### Can existing OpenAI transcription clients be pointed at Fun-ASR-Nano-API?

Yes. It exposes an OpenAI-compatible speech-to-text API.

### What language and dialect coverage does Fun-ASR-Nano support?

The model guide describes support for Chinese, English, Japanese, seven Chinese dialect groups, and 26 regional accents.

---
Source: Our Local Host (https://ourlocalhost.com/app/2838/fun-asr-nano-api), the self-hosted and open-source app directory.
