Podcast MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUDIO_DIR | No | Directory where generated audio files are written. Defaults to 'audio_output' (/tmp/podcast_audio in Docker). | audio_output |
| TTS_ENGINE | No | The TTS engine to use: 'kitten' (light, free-tier safe) or 'kokoro' (better voices, more RAM). Defaults to 'kitten'. | kitten |
| KITTEN_MODEL | No | Full-precision nano model name/path. The -int8 variant is smaller but has known quality issues. Defaults to 'KittenML/kitten-tts-nano-0.8'. | KittenML/kitten-tts-nano-0.8 |
| PRELOAD_MODEL | No | Load the model in the background at boot. Defaults to '1'. | 1 |
| KOKORO_VARIANT | No | Variant of the Kokoro model: int8 (114 MB), fp16 (164 MB), or fp32 (326 MB). Defaults to 'int8'. | int8 |
| AUDIO_TTL_HOURS | No | Delete generated files older than this many hours. Defaults to '24'. | 24 |
| PUBLIC_BASE_URL | No | Base URL for returned audio_url. Overrides RENDER_EXTERNAL_URL. If not set, uses RENDER_EXTERNAL_URL or localhost. | |
| KOKORO_MODEL_DIR | No | Directory where Kokoro model files are cached. Defaults to 'models/kokoro' (/tmp/kokoro in Docker). | models/kokoro |
| MAX_SCRIPT_CHARS | No | Reject scripts longer than this many characters. Defaults to '20000'. | 20000 |
| DEFAULT_HOST_VOICE | No | Override the default host voice. If empty, the engine default is used (kokoro: am_michael, kitten: Jasper). | |
| DEFAULT_GUEST_VOICE | No | Override the default guest voice. If empty, the engine default is used (kokoro: af_heart, kitten: Bella). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/vivekprojects-GIT/Podcast_MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server