Developer Resources

Use the Logos platform directly with SDKs, API docs, and a live transcription demo. Omnix sits on top of this stack as the flagship packaged product.

Start building with the platform

Omnix is the commercial workflow. This page is for the teams that need the underlying speech and agent stack directly.

API Documents

Interactive API documentation with live examples and endpoint details.

View API Docs →

Documentation

Explore our comprehensive API reference and getting-started guides.

Read the Docs →

Node.js SDK

The official TypeScript and JavaScript library for the Talkscriber API.

View on GitHub →

Python SDK

Integrate Talkscriber into your Python applications with our official package.

View on PyPI →

Try the live transcription demo

Try Talkscriber Real-Time STT

Click the microphone and speak for up to 2 minutes. Your audio streams directly to Talkscriber over a secure WebSocket and the transcript appears in real time.

Press the microphone and start speaking…

Click the microphone to start real-time transcription

SDK examples

"""
Basic Speech-to-Text (STT) Example

This example demonstrates the basic usage of Talkscriber's live transcription
service. It shows how to transcribe speech from a microphone in real-time.

Requirements:
- Talkscriber API key
- Microphone access
- Internet connection

Usage:
$ pip install --upgrade tsclient
$ export TALKSCRIBER_API_KEY="<your_api_key>"
"""

import os
import sys
from talkscriber.stt import TranscriptionClient


def main():
    """Basic STT example using microphone input"""
    
    # Get API key from environment variable
    api_key = os.getenv("TALKSCRIBER_API_KEY")
    if not api_key:
        print("Error: Please set your TALKSCRIBER_API_KEY environment variable")
        print("Get your API key from: https://app.talkscriber.com")
        sys.exit(1)
    
    print("=== Talkscriber Basic STT Example ===")
    print("This example will transcribe speech from your microphone in real-time.")
    print("Press Ctrl+C to stop.\n")
    
    # Create transcription client
    client = TranscriptionClient(
        host="wss://api.talkscriber.com",
        port=9090,
        api_key=api_key,
        language="en",  # English
        multilingual=False,
        translate=False,
        enable_turn_detection=True,
        turn_detection_timeout=0.6
    )
    
    try:
        print("Starting live transcription...")
        print("Speak into your microphone now!\n")
        
        # Start transcription (uses microphone by default)
        client()
        
    except KeyboardInterrupt:
        print("\n\nTranscription stopped by user.")
    except Exception as e:
        print(f"\nError during transcription: {e}")
        sys.exit(1)


if __name__ == "__main__":
    main()