Skip to content

EXPLORE THE POSSIBILITIES

Less imagining.
More trying.

Hear a voice, explore a recording and try a conversation. Experience the pieces of the PyAI platform before building them into your application.

YOUR AUDIO, MADE USEFUL

A recording. A clearer picture.

Drop a call, meeting or podcast recording to explore a speaker-labelled transcript, talk ratio and searchable clips.

Drop a call recording, or try a sample.

Up to ~3 min · diarized on PyAI Hear · your audio is processed, not stored.

See the code

Hear a voice instantly.

Tap a stock voice, or type a line and synthesize it live.

Try your words. Take the code.

Choose a voice and listen. The code follows your settings.

62 / 240 characters

MP3 · No signup

Live demo: up to 30 requests per day.

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.pyai.com/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.PYAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "pyai-speak",
    "input": "Hi, thanks for calling Acme Dental - how can I help you today?",
    "voice": "stock_ava_en_us",
    "response_format": "mp3"
  }),
});
if (!response.ok) throw new Error(await response.text());
await writeFile("speech.mp3", Buffer.from(await response.arrayBuffer()));

Set PYAI_API_KEY in your server environment. Saves your audio as speech.mp3.

Copy the code to use this text and voice, or explore the full Playground.

Open Playground

Stock voices

Instant preview

36 in the live catalog - here are a few.

Transcribe a callUpload audio and watch Hear transcribe it, with streaming partials.Export the codeTweak any example and copy a ready-to-run snippet into your app.
See the code

The live demo is rate-limited and capped. Prefer to build with an AI agent?

Live agent

Talk to PyAI - a real Omni voice agent

Tap the mic and ask about products, latency, or pricing. This is the live Omni realtime engine answering in your browser - voice in, voice out, no signup.

Talk to PyAI, live Omni agent

Tap to start a live voice call with PyAI.

Voice in, voice out. Ask anything about PyAI.

What is Omni?How fast is turn-taking?What does it cost?How do I get started?

Live demo, mic only, capped at 2 minutes. Powered by Omni over a direct browser socket.

See the code

QUESTIONS, ANSWERED

A few useful answers.

What can I try in the PyAI Playground?

You can explore a recording, preview generated speech and try an Omni voice conversation. Each demo explains what it accepts and what it produces.

Does opening the page start a microphone call?

No. A voice conversation starts when you choose to begin and grant microphone access. Recorded samples and other examples can be explored separately.

How do I build an example into my application?

Use the product quickstarts, SDK starters and documentation. Product-page builders generate code for the selected configuration; copy that code and keep API credentials on your server.

Get an API key. Make a phone agent.

Sandbox keys never bill. Fund a live key when you go to production.

Get API Key