Open Source TTS: Free Text-to-Speech Solutions

Open Source TTS: Free Text-to-Speech Solutions

💡 What You Will Learn

Open Source TTS: Free Text-to-Speech Solutions

pip install edge-tts

# Basic
edge-tts --text "" --voice zh-CN-Yunxi --write-media output.mp3

# 
edge-tts --text "AI" --voice zh-CN-YunxiNeural --write-media output.mp3

# 
edge-tts --text "" --voice zh-CN-XiaoxiaoNeural --write-media output.mp3

git clone https://github.com/2noise/ChatTTS
git clone https://huggingface.co/2noise/ChatTTS
cd ChatTTS
pip install -r requirements.txt

import ChatTTS
import torch

chat = ChatTTS.Chat()
chat.load_models()

texts = ["", ""]

wavs = chat.infer(texts, use_decoder=True)
# wavs 

pip install git+https://github.com/suno-ai/bark.git

from bark import SAMPLE_RATE, generate_audio, preload_models

preload_models()

audio_array = generate_audio("AI")

|:----|:---------:|:---:|:-----:|:-------:|

# Generate
cat script.txt | while IFS= read -r line; do
    if [ -n "$line" ]; then
        edge-tts --text "$line" \
            --voice zh-CN-YunxiNeural \
            --write-media "output_$(date +%s).mp3"
    fi
done