Generates speech with the open-weight Kokoro TTS models and saves MP3 files locally or uploads them to an S3 bucket.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add kokoro-tts -- python mcp_client.py --text 'Hello, world!'~/.codex/config.toml
[mcp_servers.kokoro-tts]
command = "python"
args = ["mcp_client.py", "--text", "Hello, world!"]
# codex mcp add kokoro-tts -- python mcp_client.py --text 'Hello, world!'~/.cursor/mcp.json
{
"mcpServers": {
"kokoro-tts": {
"command": "python",
"args": [
"mcp_client.py",
"--text",
"Hello, world!"
]
}
}
}.vscode/mcp.json
{
"servers": {
"kokoro-tts": {
"type": "stdio",
"command": "python",
"args": [
"mcp_client.py",
"--text",
"Hello, world!"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"kokoro-tts": {
"command": "python",
"args": [
"mcp_client.py",
"--text",
"Hello, world!"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"kokoro-tts": {
"command": "python",
"args": [
"mcp_client.py",
"--text",
"Hello, world!"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"kokoro-tts": {
"command": "python",
"args": [
"mcp_client.py",
"--text",
"Hello, world!"
]
}
}
}