Typecast API
About
An MCP server for the Typecast API, enabling AI-powered voice generation for various content.
Details
- Author
- neosapience
- Categories
- Cloud Service, Other, AI
Jump to
Setup
Install Typecast API in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/neosapience/typecast-api-mcp-server-sample
Follow the installation instructions in the repository README, then restart your MCP client.
MCP Server for typecast-api, enabling seamless integration with MCP clients. This project provides a standardized way to interact with Typecast API through the Model Context Protocol.
This project implements a ModelContext Protocol serverfor Typecast API, allowing MCP clients to interact with the Typecast API in a standardized way.
- 7 Emotion Presets: normal, happy, sad, angry, whisper, toneup, tonedown
- Smart Mode: AI automatically infers emotion from context usingprevious_textandnext_text
- 37 Languages: Extended language support
The MCP server exposes two tools for temporary custom voice workflows:
- clone_voice: creates a quick-cloned custom voice from a local WAV or MP3 file.
- delete_cloned_voice: deletes a cloned voice ID that starts withuc_.
- Voice name must be 1-30 characters.
- Audio sample must be WAV or MP3.
- Audio sample must be 25 MB or smaller.
- Usessfm-v30unless you have a specific compatibility reason.
- Runclone_voicewithname,audio_file_path, and optionalmodel.
- Use the returnednext_step_voice_idandnext_step_modelintext_to_speech,text_to_speech_stream, ortext_to_speech_with_timestamps.
- Rundelete_cloned_voicewhen the temporary cloned voice is no longer needed.
Userecommend_voiceswhen you know the desired style, mood, language, or use case but do not know the exact voice ID yet. It callsGET /v1/voices/recommendationsand returns candidates sorted by score.
The recommendation response intentionally contains onlyvoice_id,voice_name, andscore. If an agent needs details about a recommended voice, callget_voicefor each returned ID orget_voicesfor a broader filtered list before using the ID in TTS.
https://typecast-api-docs-web-production.up.railway.app/mcp
Without authentication, the server exposes onlysearch_documentation. Send a Typecast API key on every MCP request to unlock the Typecast API tools:
Authorization: Bearer YOUR_TYPECAST_API_KEYis also supported. The hosted server does not store the key. Generated audio is returned as a private, unguessable download URL that expires after one hour.play_audioremains a local-only tool because a hosted server cannot play sound on the MCP client's device.
To preserve how Typecast integration code was created, hosted clients may send both attribution headers together:
X-Typecast-Integration-Source: api-docs X-Typecast-Generated-By: codex
Useapi-pagefor API page onboarding andapi-docsfor API documentation onboarding. The legacyllmsandskillvalues remain accepted.X-Typecast-Generated-Byaccepts a lowercase ASCII token up to 32 characters. The server keeps its owntypecast-mcp/<version>User-Agent and appends this attribution instead of replacing it.
On the hosted server,clone_voiceaccepts onlyaudio_base64together with anaudio_filenameending in.wavor.mp3.audio_file_pathis available only when this MCP server runs locally.
Set the following environment variables:
TYPECAST_API_KEY=<your-api-key> TYPECAST_OUTPUT_DIR=<your-output-directory> # default: ~/Downloads/typecast_output TYPECAST_INTEGRATION_SOURCE=<llms|skill|api-page|api-docs> # optional; set both attribution variables TYPECAST_GENERATED_BY=<coding-agent-id> # optional; e.g. codex or claude-code
You can add the following to yourclaude_desktop_config.jsonor Cursor MCP settings:
Recommended: Using uvx (No installation required)
{ "mcpServers": { "typecast-api-mcp-server": { "command": "uvx", "args": [ "--from", "git+https://github.com/neosapience/typecast-api-mcp-server.git", "typecast-api-mcp-server" ], "env": { "TYPECAST_API_KEY": "YOUR_API_KEY", "TYPECAST_OUTPUT_DIR": "PATH/TO/YOUR/OUTPUT/DIR" } } } }
This method automatically fetches and runs the server from GitHub without manual cloning.
Note for Linux users: If you're running on Linux, you need to add theXDG_RUNTIME_DIRenvironment variable to theenvsection:
"env": { "TYPECAST_API_KEY": "YOUR_API_KEY", "TYPECAST_OUTPUT_DIR": "PATH/TO/YOUR/OUTPUT/DIR", "XDG_RUNTIME_DIR": "/run/user/1000" }
git clone https://github.com/neosapience/typecast-api-mcp-server.git cd typecast-api-mcp-server
This project requires Python 3.10 or higher and usesuvfor package management.
# Create virtual environment and install packages uv venv uv pip install -e .
{ "mcpServers": { "typecast-api-mcp-server": { "command": "uv", "args": [ "--directory", "/PATH/TO/YOUR/PROJECT", "run", "typecast-api-mcp-server" ], "env": { "TYPECAST_API_KEY": "YOUR_API_KEY", "TYPECAST_OUTPUT_DIR": "PATH/TO/YOUR/OUTPUT/DIR" } } } }
Replace/PATH/TO/YOUR/PROJECTwith the actual path where your project is located.
Contributions are always welcome! Feel free to submit a Pull Request.
Hosted MCP server for AudioPod's audio AI: text-to-speech, voice cloning, music generation, stem and speaker separation, transcription, denoise, and voice conversion.
Interact with MiniMax's powerful APIs for text-to-speech, voice cloning, and video/image generation.
A JavaScript/TypeScript server for MiniMax MCP, offering image/video generation, text-to-speech, and voice cloning.
Interact with MiniMax's powerful Text-to-Speech, image, and video generation APIs.
Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.
MCP-native AI media generation with x402 pay-per-call. Image, video, audio, and music from 6 providers — composable via resource IDs. USDC on Base.
AI audio tools for music producers — stem splitting, vocal removal, BPM/key detection, audio-to-MIDI, format conversion and AI song generation
An MCP server for GPT-SoVITS, providing text-to-speech synthesis, voice cloning, and multi-language support.
Official SynClub server for AI generation, including text-to-speech, voice cloning, video, and image creation.
Provides speech-to-text, diarization, translation, and text summarization via the Whissle AI API.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
