Configuration

Overview

This guide covers advanced configuration options for customizing your TTS Docker deployment. Learn how to optimize resources, configure external services, and tune performance.

Environment Variables

All configuration is managed through environment variables in the .env file.

Core Configuration

LICENSE_KEY

stringRequired

Your Smallest.ai license key for validation and usage reporting

API Server Configuration

API_SERVER_PORT

integerDefaults to 7100

Port for the API server to listen on

$ API_SERVER_PORT=8080

API_BASE_URL

stringDefaults to http://license-proxy:3369

Internal URL for license proxy communication

LIGHTNING_TTS_BASE_URL

stringDefaults to http://lightning-tts:8876

Internal URL for Lightning TTS communication

Lightning TTS Configuration

TTS_PORT

integerDefaults to 8876

Port for Lightning TTS to listen on

$ TTS_PORT=8876

REDIS_URL

stringDefaults to redis://redis:6379

Redis connection URL for caching and state management

For external Redis:

$ REDIS_URL=redis://external-redis.example.com:6379

With password:

$ REDIS_URL=redis://:password@redis:6379

GPU_DEVICE_ID

stringDefaults to 0

GPU device ID to use (for multi-GPU systems)

$ GPU_DEVICE_ID=0

Resource Configuration

GPU Allocation

For systems with multiple GPUs, you can specify which GPU to use:

docker-compose.yml

1 lightning-tts:
2   deploy:
3     resources:
4       reservations:
5         devices:
6           - driver: nvidia
7             device_ids: ['0']
8             capabilities: [gpu]

For multiple GPUs per container:

docker-compose.yml

1 lightning-tts:
2   deploy:
3     resources:
4       reservations:
5         devices:
6           - driver: nvidia
7             count: 2
8             capabilities: [gpu]

Memory Limits

Set memory limits to prevent resource exhaustion:

docker-compose.yml

1 services:
2   lightning-tts:
3     deploy:
4       resources:
5         limits:
6           memory: 16G
7         reservations:
8           memory: 12G

CPU Limits

Control CPU allocation:

docker-compose.yml

1 services:
2   lightning-tts:
3     deploy:
4       resources:
5         limits:
6           cpus: '8'
7         reservations:
8           cpus: '4'

External Services

External Redis

Use an external Redis instance instead of the embedded one:

docker-compose.yml

1 services:
2   api-server:
3     environment:
4       - REDIS_HOST=external-redis.example.com
5       - REDIS_PORT=6379
6       - REDIS_PASSWORD=${REDIS_PASSWORD}
7 
8   lightning-tts:
9     environment:
10       - REDIS_HOST=external-redis.example.com
11       - REDIS_PORT=6379
12       - REDIS_PASSWORD=${REDIS_PASSWORD}

Remove the Redis service from docker-compose.yml.

Custom Network

Use a custom Docker network:

docker-compose.yml

1 networks:
2   custom-network:
3     driver: bridge
4     name: my-custom-network
5 
6 services:
7   api-server:
8     networks:
9       - custom-network

Performance Tuning

Voice Configuration

Configure voice parameters:

docker-compose.yml

1 lightning-tts:
2   environment:
3     - DEFAULT_VOICE=default
4     - VOICE_SPEED=1.0
5     - VOICE_PITCH=1.0

Batch Processing

Optimize for batch processing:

docker-compose.yml

1 lightning-tts:
2   environment:
3     - BATCH_SIZE=8
4     - MAX_QUEUE_SIZE=100

Model Precision

Control model precision for performance:

docker-compose.yml

1 lightning-tts:
2   environment:
3     - MODEL_PRECISION=fp16

Options: fp32, fp16, int8

Volume Mounts

Persistent Model Cache

Cache models to avoid re-downloading:

docker-compose.yml

1 services:
2   lightning-tts:
3     volumes:
4       - tts-models:/app/models
5 
6 volumes:
7   tts-models:

Log Persistence

Persist logs for debugging:

docker-compose.yml

1 services:
2   api-server:
3     volumes:
4       - ./logs/api-server:/app/logs
5   
6   lightning-tts:
7     volumes:
8       - ./logs/tts:/app/logs

Health Checks

Add health checks for better monitoring:

docker-compose.yml

1 services:
2   lightning-tts:
3     healthcheck:
4       test: ["CMD", "curl", "-f", "http://localhost:8876/health"]
5       interval: 30s
6       timeout: 10s
7       retries: 3
8       start_period: 60s
9 
10   api-server:
11     healthcheck:
12       test: ["CMD", "curl", "-f", "http://localhost:7100/health"]
13       interval: 30s
14       timeout: 10s
15       retries: 3

Security Configuration

Read-Only Root Filesystem

Enhance security with read-only root filesystem:

docker-compose.yml

1 services:
2   api-server:
3     read_only: true
4     tmpfs:
5       - /tmp
6       - /var/tmp

Non-Root User

Run containers as non-root:

docker-compose.yml

1 services:
2   api-server:
3     user: "1000:1000"

Environment File Example

Complete .env file example:

.env

$ LICENSE_KEY=your-license-key-here
$ 
$ API_SERVER_PORT=7100
$ TTS_PORT=8876
$ 
$ REDIS_HOST=redis
$ REDIS_PORT=6379
$ 
$ GPU_DEVICE_ID=0
$ 
$ DEFAULT_VOICE=default
$ VOICE_SPEED=1.0

What’s Next?

TTS Services Overview

Learn about each TTS service component

TTS Troubleshooting

Debug configuration issues

1	lightning-tts:
2	deploy:
3	resources:
4	reservations:
5	devices:
6	- driver: nvidia
7	device_ids: ['0']
8	capabilities: [gpu]

1	services:
2	lightning-tts:
3	deploy:
4	resources:
5	limits:
6	memory: 16G
7	reservations:
8	memory: 12G

1	services:
2	api-server:
3	environment:
4	- REDIS_HOST=external-redis.example.com
5	- REDIS_PORT=6379
6	- REDIS_PASSWORD=${REDIS_PASSWORD}
7
8	lightning-tts:
9	environment:
10	- REDIS_HOST=external-redis.example.com
11	- REDIS_PORT=6379
12	- REDIS_PASSWORD=${REDIS_PASSWORD}

1	networks:
2	custom-network:
3	driver: bridge
4	name: my-custom-network
5
6	services:
7	api-server:
8	networks:
9	- custom-network

1	lightning-tts:
2	environment:
3	- DEFAULT_VOICE=default
4	- VOICE_SPEED=1.0
5	- VOICE_PITCH=1.0

1	lightning-tts:
2	environment:
3	- BATCH_SIZE=8
4	- MAX_QUEUE_SIZE=100

1	services:
2	lightning-tts:
3	volumes:
4	- tts-models:/app/models
5
6	volumes:
7	tts-models:

1	services:
2	lightning-tts:
3	healthcheck:
4	test: ["CMD", "curl", "-f", "http://localhost:8876/health"]
5	interval: 30s
6	timeout: 10s
7	retries: 3
8	start_period: 60s
9
10	api-server:
11	healthcheck:
12	test: ["CMD", "curl", "-f", "http://localhost:7100/health"]
13	interval: 30s
14	timeout: 10s
15	retries: 3

1	services:
2	api-server:
3	read_only: true
4	tmpfs:
5	- /tmp
6	- /var/tmp

$	LICENSE_KEY=your-license-key-here
$
$	API_SERVER_PORT=7100
$	TTS_PORT=8876
$
$	REDIS_HOST=redis
$	REDIS_PORT=6379
$
$	GPU_DEVICE_ID=0
$
$	DEFAULT_VOICE=default
$	VOICE_SPEED=1.0