Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
FROM python:3.10-slim
ARG FUNASR_VERSION=1.3.29
ARG VERSION=0.1.2
ARG VCS_REF=unknown
LABEL io.modelcontextprotocol.server.name="io.github.modelscope/funasr-mcp" \
org.opencontainers.image.title="FunASR MCP Server" \
org.opencontainers.image.description="Local speech transcription over the Model Context Protocol" \
org.opencontainers.image.source="https://github.com/modelscope/FunASR" \
org.opencontainers.image.version="${VERSION}" \
org.opencontainers.image.revision="${VCS_REF}" \
org.opencontainers.image.licenses="MIT"
ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
PIP_NO_CACHE_DIR=1 \
FUNASR_DEVICE=cpu
WORKDIR /app
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
ffmpeg \
libsndfile1 \
&& rm -rf /var/lib/apt/lists/*
RUN pip install "funasr==${FUNASR_VERSION}"
COPY funasr_mcp.py /app/funasr_mcp.py
CMD ["python", "/app/funasr_mcp.py"]