Speak
A voiceover, from a sentence.
“Turn this welcome message into warm, natural speech and give me the audio.”
list_voices → synthesize_speech
PyAI × your AI app
Natural voice.
Now in your flow.
Make something you can hear. Build an agent that can listen. Bring PyAI into ChatGPT, Claude, Cursor, Codex and Devin with one connection.
One URL. Browser sign-in. Your chosen project.
Your app. Your PyAI project.
Browser sign-inConnect Cursor to PyAI
Install PyAI, enable the server in Cursor, and complete the browser connection.
.cursor/mcp.json
{
"mcpServers": {
"pyai": {
"url": "https://api.pyai.com/mcp"
}
}
}Sign in → select a project → approve access. Cursor setup reference
01 / Ask. Create. Keep going.
Seven ways to put voice to work.
Start with the result you want. Your AI app discovers the tools, checks the inputs and works with your authorized PyAI project.
Hear
From recording to readable.
“Transcribe this interview and help me find the key moments.”
transcribe_audio · transcription jobs
Agents
Build your next voice agent.
“Create a booking assistant with a greeting, clear boundaries and a human handoff.”
create_agent · tools · knowledge
Trace
Find the evidence in your calls.
“Find calls with missing disclosures and show the supporting evidence.”
interactions · findings · rule packs
Recap
A useful summary. Next steps, too.
“Summarize this sales call and extract objections and follow-up actions.”
create_recap → get_recap
Dub
Let your recording travel.
“Dub this English recording into Hindi and give me the finished audio.”
capabilities → job → audio
Cast
Give your script some direction.
“Turn this script into expressive narration. Preview a line before the full render.”
direct → preview → render
02 / A connection you control
Sign in once. Pick where you work.
Your app opens PyAI in the browser. Choose the project, review what the app can do, and connect.
Browser authorization
OAuth keeps credentials out of your prompts and shared configuration. Your app receives access to the project you approve.
Local and remote
Use the hosted URL in chat apps. Prefer a local process? The npm server reuses your saved PyAI CLI login and profiles.
Ready for agents
Typed tools, structured results, workflow recipes, readable errors and playable audio help your agent get useful work done.
03 / Give your agent a head start
Less guessing. More building.
Public Markdown, live tool discovery and the API contract give coding agents the details they need.
MCP handbookSetup, workflows, auth, updates and troubleshooting.Agent instructionsInputs, permissions, job polling and error recovery.Tool schemasA generated JSON snapshot. Live tools/list is authoritative.
Give this to your agent
Use the connected PyAI MCP server.
Read get_started and check whoami.
Discover the tools for my use case before acting.
Use https://pyai.com/mcp-agent-guide.md for conventions.
Keep job IDs and return usable audio or transcripts.Prefer local stdio? Reuse your CLI login.
Node.js 22+ · terminal
npx -y @pyai/mcp@latest login
# Then configure your host to launch:
npx -y @pyai/mcp@latestAlready ran pyai login? The MCP server uses that saved profile. Full local setup.
A few things worth knowing.
What is PyAI MCP?
PyAI MCP connects AI apps to the PyAI voice APIs through typed tools. Use it to generate speech, transcribe audio, manage voice Agent profiles, review compliance, summarize calls, dub recordings and render directed narration.
Do I need to copy an API key?
The remote connection uses browser OAuth. Sign in to PyAI, select a project and approve the requested permissions. Your AI app receives a scoped connection; your PyAI API key stays on the server.
Can I connect in ten seconds?
An existing signed-in user can go straight to project consent. Setup time also depends on your app, account and workspace policy. A new account or an administrator approval can take longer.
Will it appear automatically in ChatGPT or Claude?
Use a custom app or connector to add PyAI by URL. Public app-directory listings require separate submission and review. Your host’s plan and workspace policies determine whether custom connections and write tools are available.
Can MCP run a live voice call?
MCP can create and configure reusable voice Agent profiles. Live microphone and telephone conversations run through the PyAI SDK, widget or telephony integration. Creating a profile does not place a call.
How do updates work?
PyAI updates the hosted endpoint through its deployment process. Local @pyai/mcp installations have their own package releases and need restarting after an upgrade. The CLI ships in @pyai/sdk; installed versions do not silently upgrade when a new SDK is released.
How do I disconnect an app?
Open Connected AI apps in the PyAI console and revoke the connection. Access lasts up to 30 days and also stops when the authorizing user loses project access. Revocation stops new requests; already-submitted jobs may continue.
What does it cost?
The MCP connection uses your project’s normal PyAI credits, product pricing and limits. Generated audio, transcription, dubbing and other processing consume usage. Reading the in-server setup guide and workflow recipes does not consume model credits.