Kokoro Text to Speech MCP Server
by mberg
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug mode (set to "true" or "1") | |
| MCP_HOST | No | Host to bind the server to | 0.0.0.0 |
| MCP_PORT | No | Port to listen on | 9876 |
| TTS_SPEED | No | Default speed for the TTS client | 1.0 |
| TTS_VOICE | No | Default voice for the TTS client | af_heart |
| AWS_REGION | No | S3 region (e.g., us-east-1) | us-east-1 |
| MP3_FOLDER | No | Path to store MP3 files (default is 'mp3' folder in script directory) | |
| S3_ENABLED | No | Enable S3 uploads (set to "true" or "1") | true |
| TTS_LANGUAGE | No | Default language for the TTS client | en-us |
| AWS_S3_FOLDER | No | Folder path within the S3 bucket | mp3 |
| MCP_CLIENT_HOST | No | Hostname for client connections to the server | localhost |
| AWS_ACCESS_KEY_ID | No | Your AWS access key ID | |
| AWS_S3_BUCKET_NAME | No | S3 bucket name | |
| MP3_RETENTION_DAYS | No | Number of days to keep MP3 files before automatic deletion | |
| AWS_S3_ENDPOINT_URL | No | Optional custom endpoint URL for S3-compatible storage | |
| AWS_SECRET_ACCESS_KEY | No | Your AWS secret access key | |
| DELETE_LOCAL_AFTER_S3_UPLOAD | No | Whether to delete local MP3 files after successful S3 upload (set to "true" or "1") |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |