skills.rest
framerslab
framerslabOFFICIAL
Explore all skills by this author →
Website𝕏@framerslabGitHub

streaming-stt-whisper

Transcribe live speech in real time using the OpenAI Whisper API.

1|Updated Feb 8, 2026
Search Tags:#OpenAI#Whisper#real-time#streaming#speech-to-text
One-click install
npx skills add https://github.com/framerslab/agentos-skills --skill streaming-stt-whisper
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: streaming-stt-whisper
Source: https://github.com/framerslab/agentos-skills/tree/main/registry/curated/streaming-stt-whisper
Command: npx skills add https://github.com/framerslab/agentos-skills --skill streaming-stt-whisper

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) components.

What problem does it solve?

This Skill addresses the need for real-time speech-to-text transcription, providing a seamless experience with offline compatibility and flexibility in endpoint choice.

Core Features & Use Cases

  • Real-time Transcription: Offers immediate speech-to-text conversion for live voice sessions.
  • Offline Compatibility: Supports local Whisper-compatible servers like Faster-Whisper and Groq.
  • Use Case: Ideal for applications requiring live speech transcription, such as voice assistants or interactive voice response systems.

Quick Start

Activate the streaming-stt-whisper skill to transcribe live speech during your session.

Frequently Asked Questions about streaming-stt-whisper

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

FAQPage Schema
How do I get real-time speech-to-text transcription for live voice sessions?▼

Real-time speech-to-text transcription for live voice sessions is provided by streaming audio input directly to the OpenAI Whisper API. This skill activates during your session to offer immediate voice conversion.

Can I use local Whisper-compatible servers for offline speech-to-text transcription?▼

Offline speech-to-text transcription is supported by configuring the skill to use local Whisper-compatible servers. You can route requests to local endpoints like Faster-Whisper or Groq instead of the cloud API.

Do I need an OpenAI API key to use Whisper for streaming speech-to-text?▼

An OpenAI API key is required to authenticate streaming speech-to-text requests via the Whisper API. If you use a local offline server, you can bypass the cloud key requirement by configuring your local endpoint.

What is the best way to transcribe live speech for a voice assistant application?▼

Transcribing live speech for voice assistants is best handled by streaming audio to the Whisper API for immediate text results. This skill is specifically ideal for interactive voice response systems requiring low-latency conversion.

Does streaming speech-to-text with OpenAI Whisper work without an internet connection?▼

Streaming speech-to-text with OpenAI Whisper works offline by connecting to a local Whisper-compatible server. You must configure the optional local endpoint setting to route transcription requests without an internet connection.

Why does real-time speech-to-text require configuring local endpoints for Faster-Whisper?▼

Configuring local endpoints for Faster-Whisper is required for real-time speech-to-text when operating offline. This setup redirects the audio stream from the OpenAI cloud API to your local server to process transcriptions.

Related Skills

ClaudioCeppi83ClaudioCeppi83

openai-whisper

Transcribe audio files to text using the OpenAI Whisper CLI.

Community
Basic
reedmayhew18reedmayhew18
23

oc-voice

Transcribe voice chat messages with Whisper and route text downstream.

Community
Intermediate
harshav167harshav167

speech-recognition

Transcribe live microphone or pre-recorded audio into text using Apple's Speech framework.

Community
Advanced
steipetesteipete
385.7k

openai-whisper

Transcribe local audio files to text or subtitles using the Whisper CLI.

Community
Intermediate