# Typecast — how to use (mcp.ai)

Connect your Typecast account and use 7 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Typecast is an AI voice platform for generating expressive speech, discovering voices, and managing custom voices.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_typecast?ms=1787295780000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `typecast_compose_speech`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/typecast`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/typecast/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/typecast/compose/speech` — Generate one audio file from an ordered sequence of speech and pause segments.
  - body: { segments: object[], audio_format?: string }
- `POST https://api.mcp.ai/api/typecast/generate/speech` — Generate a complete WAV or MP3 audio file from text using a Typecast voice.
  - body: { seed?: integer, text: string, model: string, prompt?: object, volume?: integer, language?: string, voice_id: string, audio_pitch?: integer, audio_tempo?: number, target_lufs?: number, audio_format?: string }
- `POST https://api.mcp.ai/api/typecast/generate/speech/with/timestamps` — Generate speech plus word, character, or both alignment timestamp arrays.
  - body: { seed?: integer, text: string, model: string, prompt?: object, volume?: integer, language?: string, voice_id: string, audio_pitch?: integer, audio_tempo?: number, granularity?: string, target_lufs?: number, audio_format?: string }
- `POST https://api.mcp.ai/api/typecast/get/subscription` — Get the connected Typecast API plan, credit usage, concurrency limit, and custom-voice allowance.
- `POST https://api.mcp.ai/api/typecast/get/voice` — Get one voice's metadata, supported models, and available emotions by voice ID.
  - body: { voice_id: string }
- `POST https://api.mcp.ai/api/typecast/list/voices` — List available built-in and owned custom Typecast voices, optionally filtered by speech model, gender, age, use case, and voice type. Returns each voice ID with the model versions and emotions it supp
  - body: { age?: string, model?: string, gender?: string, use_cases?: string, voice_type?: string }
- `POST https://api.mcp.ai/api/typecast/recommend/voices` — Find and rank Typecast voices that match a natural-language description.
  - body: { count?: integer, query: string }

## Example prompts
- "What can I do in Typecast?"
- "Show me a summary of my Typecast account"

## More
- Page: https://mcp.ai/typecast
- Agent spec (llms.txt): https://mcp.ai/typecast/llms.txt
- Postman collection: https://mcp.ai/typecast/postman.json