Palabra API Overview

Real-time speech translation

Add Palabra's world-class translation to your app in minutes with our intuitive API and ready-made client libraries

Python
JavaScript
More

import asyncio
import time
from palabra_ai import Palabra, Transcript, Audio

CHUNK_MS = 320  # ~320 ms of PCM (s16le, 24 kHz, mono)

async def main():
    palabra = Palabra()

    async with palabra.translation(source="en", targets=["es"]) as session:

        async def send_audio():
            next_send = time.monotonic()
            while chunk := await audio_buffer.get():  # your audio source
                await session.send_audio(chunk)
                next_send += CHUNK_MS / 1000
                await asyncio.sleep(max(0, next_send - time.monotonic()))
            await session.end()

        sender = asyncio.create_task(send_audio())

        async for event in session:
            match event:
                case Transcript():
                    print(event)
                case Audio():
                    play(event.pcm)

        await sender

asyncio.run(main())

Python Palabra SDK

import { Room } from 'livekit-client';

// Your backend creates a temporary session and returns its data object.
// The browser receives session.token and session.webrtc.url, never an API Key.
const room = new Room();
await room.connect(session.webrtc.url, session.token, { autoSubscribe: true });

WebRTC Quick Start

Overview

The Palabra API enables real-time speech translation across multiple languages, helping your users communicate clearly and efficiently. With easy integration for both client- and server-side apps, Palabra fits seamlessly into any business workflow.