Coqui TTS Quick Start Guide
This document provides a comprehensive guide to installing, configuring, and using Coqui TTS, an open-source text-to-speech toolkit. It explains TTS and vocoder concepts, environment setup, model management, API usage, and log configuration for production deployment.
Introduction
Coqui TTS is an open-source Text-to-Speech (TTS) toolkit developed by Coqui AI.
It provides:
- Pre-trained models
- Training / fine-tuning pipelines
- Speech synthesis APIs and CLI tools
Official Resources
Environment Setup
Virtual environment path:
ls /root/tts-venv/Start/Stop control (via Supervisor):
supervisorctl statusConfiguration file path:
cat /etc/supervisor/conf.d/tts-server.confLog Files
| Log Type | Path |
|---|---|
| Error log | /var/log/tts-server.err.log |
| Output log | /var/log/tts-server.out.log |
Common Commands & Model Switching
List available models
tts --list_modelsRun TTS with a pre-trained model
tts --text "Text for TTS" \
--model_name "tts_models/en/ek1/tacotron2" \
--out_path output.wavSwitch to another model (via configuration)
Edit the Supervisor config:
vim /etc/supervisor/conf.d/tts-server.confExample:
[program:tts-server]
command=/root/tts-venv/bin/tts-server --model_name "tts_models/en/sam/tacotron-DDC" --use_cuda true
directory=/root
autostart=true
autorestart=true
stderr_logfile=/var/log/tts-server.err.log
stdout_logfile=/var/log/tts-server.out.log
user=root
environment=COQUI_TOS_AGREED="1",TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD="1"Save the file and restart the service:
supervisorctl reload
# Output:
# Restarted supervisordAPI Test
Refer to the official Python inference API guide:
👉 https://docs.coqui.ai/en/latest/inference.html#python-tts-api
Outline