wehub-resource-sync
128 lines
4.2 KiB
YAML
128 lines
4.2 KiB
YAML
# Docker Compose with Speaches (Local TTS/STT)
|
|
#
|
|
# This setup includes Speaches for free, private speech processing:
|
|
# - Text-to-Speech (TTS): Generate podcast audio locally
|
|
# - Speech-to-Text (STT): Transcribe audio/video content locally
|
|
#
|
|
# Why Speaches?
|
|
# - Free: No per-minute/per-character costs
|
|
# - Private: Audio never leaves your machine
|
|
# - Offline: Works without internet
|
|
# - OpenAI-compatible: Drop-in replacement for OpenAI TTS/STT
|
|
#
|
|
# Usage:
|
|
# 1. Copy this file to your project folder as docker-compose.yml
|
|
# 2. Change OPEN_NOTEBOOK_ENCRYPTION_KEY below
|
|
# 3. Run: docker compose up -d
|
|
# 4. Download models (see instructions below)
|
|
# 5. Configure in UI: Settings → API Keys → Add OpenAI-Compatible
|
|
#
|
|
# Full documentation:
|
|
# - TTS setup: https://github.com/lfnovo/open-notebook/blob/main/docs/5-CONFIGURATION/local-tts.md
|
|
# - STT setup: https://github.com/lfnovo/open-notebook/blob/main/docs/5-CONFIGURATION/local-stt.md
|
|
|
|
services:
|
|
surrealdb:
|
|
image: surrealdb/surrealdb:v2
|
|
command: start --log info --user root --pass root rocksdb:/mydata/mydatabase.db
|
|
user: root
|
|
ports:
|
|
# Localhost only — the database uses default credentials, so never
|
|
# publish this port on 0.0.0.0
|
|
- "127.0.0.1:8000:8000"
|
|
volumes:
|
|
- ./surreal_data:/mydata
|
|
environment:
|
|
- SURREAL_EXPERIMENTAL_GRAPHQL=true
|
|
restart: always
|
|
pull_policy: always
|
|
|
|
speaches:
|
|
image: ghcr.io/speaches-ai/speaches:latest-cpu
|
|
container_name: speaches
|
|
ports:
|
|
- "8969:8000"
|
|
volumes:
|
|
- hf-hub-cache:/home/ubuntu/.cache/huggingface/hub
|
|
restart: unless-stopped
|
|
# For GPU acceleration, use: ghcr.io/speaches-ai/speaches:latest-cuda
|
|
# and add GPU device mapping (see docs/5-CONFIGURATION/local-tts.md)
|
|
|
|
open_notebook:
|
|
image: lfnovo/open_notebook:v1-latest
|
|
ports:
|
|
- "8502:8502"
|
|
- "5055:5055"
|
|
environment:
|
|
# REQUIRED: Change this to your own secret string
|
|
- OPEN_NOTEBOOK_ENCRYPTION_KEY=change-me-to-a-secret-string
|
|
|
|
# Database connection
|
|
- SURREAL_URL=ws://surrealdb:8000/rpc
|
|
- SURREAL_USER=root
|
|
- SURREAL_PASSWORD=root
|
|
- SURREAL_NAMESPACE=open_notebook
|
|
- SURREAL_DATABASE=open_notebook
|
|
volumes:
|
|
- ./notebook_data:/app/data
|
|
depends_on:
|
|
- surrealdb
|
|
- speaches
|
|
restart: always
|
|
pull_policy: always
|
|
|
|
volumes:
|
|
hf-hub-cache:
|
|
|
|
# ==========================================
|
|
# AFTER STARTING: Download Speech Models
|
|
# ==========================================
|
|
#
|
|
# For TTS (Text-to-Speech):
|
|
# docker compose exec speaches uv tool run speaches-cli model download speaches-ai/Kokoro-82M-v1.0-ONNX
|
|
#
|
|
# For STT (Speech-to-Text):
|
|
# docker compose exec speaches uv tool run speaches-cli model download Systran/faster-whisper-small
|
|
#
|
|
# ==========================================
|
|
# CONFIGURATION IN OPEN NOTEBOOK
|
|
# ==========================================
|
|
#
|
|
# 1. Go to Settings → API Keys
|
|
# 2. Click "Add Credential" → Select "OpenAI-Compatible"
|
|
# 3. Configure:
|
|
# - Name: "Local Speaches"
|
|
# - Base URL for TTS: http://host.docker.internal:8969/v1 (macOS/Windows)
|
|
# or: http://172.17.0.1:8969/v1 (Linux)
|
|
# - Base URL for STT: (same as TTS)
|
|
# 4. Click Save → Test Connection
|
|
#
|
|
# 5. Go to Settings → Models
|
|
# 6. Add TTS Model:
|
|
# - Provider: openai_compatible
|
|
# - Model Name: speaches-ai/Kokoro-82M-v1.0-ONNX
|
|
# - Display Name: Local TTS
|
|
#
|
|
# 7. Add STT Model:
|
|
# - Provider: openai_compatible
|
|
# - Model Name: Systran/faster-whisper-small
|
|
# - Display Name: Local Whisper
|
|
#
|
|
# ==========================================
|
|
# TESTING
|
|
# ==========================================
|
|
#
|
|
# Test TTS:
|
|
# curl "http://localhost:8969/v1/audio/speech" -s \
|
|
# -H "Content-Type: application/json" \
|
|
# --output test.mp3 \
|
|
# --data '{"input": "Hello, local TTS works!", "model": "speaches-ai/Kokoro-82M-v1.0-ONNX", "voice": "af_bella"}'
|
|
#
|
|
# Test STT:
|
|
# curl "http://localhost:8969/v1/audio/transcriptions" \
|
|
# -F "file=@test.mp3" \
|
|
# -F "model=Systran/faster-whisper-small"
|
|
#
|
|
# Available voices: af_bella, af_sarah, am_adam, am_michael, bf_emma, bm_george
|
|
# Available models: See docs/5-CONFIGURATION/local-stt.md for model sizes
|