telnyx-voice-streaming-python

Stream, fork, and transcribe live voice calls via the Telnyx Python SDK.

3|2|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/team-telnyx/telnyx-toolkit --skill telnyx-voice-streaming-python-team-telnyx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: telnyx-voice-streaming-python
Source: https://github.com/team-telnyx/telnyx-toolkit/tree/main/api/python/telnyx-voice-streaming-python
Command: npx skills add https://github.com/team-telnyx/telnyx-toolkit --skill telnyx-voice-streaming-python-team-telnyx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables real-time processing of call audio, allowing for live transcription, media forking to external systems, and immediate analysis of voice data.

Core Features & Use Cases

  • Real-time Call Streaming: Stream audio from ongoing calls to WebSockets or Dialogflow.
  • Media Forking: Duplicate call media to external destinations for processing or recording.
  • Live Transcription: Convert spoken words into text as the call happens.
  • Use Case: Integrate live call sentiment analysis by streaming audio to an AI model, or fork call audio to a separate recording system.

Quick Start

Use the telnyx-voice-streaming-python skill to start streaming audio from call control ID '12345'.

Frequently Asked Questions about telnyx-voice-streaming-python

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stream voice calls in real-time using Python?

To stream voice calls in real-time, use the Telnyx Python SDK to fork and send ongoing call audio to WebSockets or external destinations for immediate processing.

Can I get live transcription for ongoing phone calls?

Yes, you can get live transcription for ongoing phone calls by streaming the call audio to an AI model, which converts the spoken words into text as the call happens.

What is media forking and when do I need it for call audio?

Media forking duplicates call audio to external destinations. You need it when routing real-time voice data to separate recording systems or AI integrations for immediate analysis.

Do I need a Telnyx API key to fork call audio?

Yes, you need a Telnyx API key to fork and stream call audio. You must also configure webhooks to handle events for specific call control IDs.

Does the Telnyx Python SDK support streaming audio to Dialogflow?

Yes, the Telnyx Python SDK supports streaming real-time call audio directly to Dialogflow, enabling live voice analytics and conversational AI integrations for ongoing calls.

What's the best way to integrate live call sentiment analysis?

The best way to integrate live call sentiment analysis is by streaming real-time call audio to an AI model using the Telnyx Python SDK for immediate voice data processing.