Skip to content

Using this repo in n8n #30

@nuaimat

Description

@nuaimat

Hello,
Thank you so much for all this amazing work.
I totally understand the purpose of this code is to provide Home Assistant with local TTS capability.
but here's how I'm using it with my local n8n

in my n8n docker-compose file, I used both wyoming-piper and wyoming-whisper like this:

services:
  n8n:
    image: docker.n8n.io/n8nio/n8n
    restart: always
    ports:
      - "127.0.0.1:5678:5678"
    environment:
      - N8N_ENFORCE_SETTINGS_FILE_PERMISSIONS=true
      - N8N_HOST=${SUBDOMAIN}.${DOMAIN_NAME}
      - N8N_PORT=5678
      - N8N_PROTOCOL=https
      - N8N_RUNNERS_ENABLED=true
      - N8N_PROXY_HOPS=1
      - NODE_ENV=production
      - WEBHOOK_URL=https://${SUBDOMAIN}.${DOMAIN_NAME}/
      - GENERIC_TIMEZONE=${GENERIC_TIMEZONE}
      - TZ=${GENERIC_TIMEZONE}
    volumes:
      - n8n_data:/home/node/.n8n
      - ./local-files:/files

  wyoming-whisper:
    image: rhasspy/wyoming-whisper
    container_name: wyoming-whisper
    restart: unless-stopped
    ports:
      - "10300:10300"
    volumes:
      - ./wyoming-whisper/data:/data
    command: ["--model", "tiny-int8", "--language", "en"]

  wyoming-piper:
    image: rhasspy/wyoming-piper
    container_name: wyoming-piper
    restart: unless-stopped
    ports:
      - "10200:10200"
    volumes:
      - ./wyoming-piper/data:/data
    command: ["--length-scale", "0.25", "--voice", "en_US-lessac-medium", "--debug"]

volumes:
  n8n_data:

and inside n8n, I installed https://www.npmjs.com/package/n8n-nodes-wyoming node (n8n > settings > community nodes)
I can use both STT (Whisper) and TTS (Piper) just fine. The problem I have is that the generated voice sounds really weird. I don't know how to describe it; I suspect it's just slow, so I tried adding.

"--length-scale", "0.25"

to the docker command.

here are two samples of the generated audio, one using en_US-amy-medium voice and the other using en_US-lessac-medium:
en_US-amy-medium_tts_output_0.wav
en_US-lessac-medium_hi_there_tts_output_0.wav

I know this might not be the main goal of this repo, but asking here is definitely worth a shot.

Thank you, and I appreciate your input. Feel free to ask any clarifying questions.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions