🚀 RealTimeX v1.0.6 is live! Update now →
RealTimeX Docs LogoRealTimeX Docs
(opens in a new tab)DiscordDiscord (opens in a new tab)
  • â–˛ Home
  • RealTimeX Roadmap
  • Getting Started
  • Introduction
    • All Features
    • AI Agents
    • API Access
    • Appearance Customization
    • Chat Logs
    • Chat Modes
    • Event Logs
    • Embedding Models
    • Language Models
    • Transcription Models
    • Voice Chat (Hands‑Free)
    • Speech‑to‑Text (Walkie‑Talkie)
    • Vector Database
    • Privacy & Data Handling
    • System Prompt Variables
    • Authenticated Scraping
    • Embedded Chat Widgets
      • Overview
        • RealTimeX Default
        • LM Studio
        • Local AI
        • Ollama
        • OpenAI
        • Azure OpenAI
        • Cohere
      • Overview
        • RealTimeX Default
        • LM Studio
        • Local AI
        • Ollama
        • KobaldCPP
        • Anthropic
        • Azure OpenAI
        • AWS Bedrock
        • Cohere
        • Google Gemini
        • Groq
        • Hugging Face
        • Mistral AI
        • OpenAI
        • OpenAI (generic)
        • OpenRouter
        • Perplexity AI
        • Together AI
        • APIpie
      • Overview
        • RealTimeX Default
        • OpenAI
      • Overview
        • LanceDB
        • Chroma
        • Milvus
        • AstraDB
        • Pinecone
        • QDrant
        • Weaviate
        • Zilliz
  • Chat Interface overview
  • Other configurations
  • RealTimeX Marketplace
  • What is the Marketplace?
  • Installation Guides
    • Overview
    • System Requirements
    • Install for MacOS
    • Install for Windows
    • Install for Linux
    • Desktop FAQ
    • Update RealTimeX
    • Where is my data stored?
    • Debugging & Logs
    • Manual Dependency Install
    • Uninstall RealTimeX
    • Overview
    • Limitations
    • 502 Error on RealTimeX Hosted
  • Guides
    • Overview
    • MCP on Desktop
    • MCP on Cloud
    • What is an Agent Flow?
    • Getting Started with Flows
    • Tutorial: HackerNews Flow
      • Overview
      • Default Blocks
      • Web Scraper
      • API Call
      • LLM Instruction
      • Read File
      • Write File
    • Debugging flows
    • Overview
    • Setup
    • Usage
      • Introduction
      • Developer Guide
      • plugin.json reference
      • handler.js reference
  • Importing custom models
    • Install the RealTimeX Browser Extension
    • What is NVIDIA NIM?
    • System Requirements
    • Installation Walkthrough
  • Frequently Asked Questions
  • LLM not using my docs!
  • AI Agent not using tools!
  • Ollama Connection Debugging
  • Fetch failed error on embed
  • Manual QNN Model Download
  • More
    • What are beta previews?
    • Enable feature previews
      • Live document sync
      • AI Computer use
    • Overview
    • v1.0.6
    • v1.0.5
    • v1.0.4
  • Contribute
  • Support
  • Contact Us
  • Sponsor RealTimeX

On This Page

  • Supported Transcription Model Providers
  • Local Transcription Model Providers
  • Cloud Transcription Model Providers
Edit this page
Feature Overview
Transcription Models

Transcription Models

RealTimeX supports both local and cloud-based audio transcription providers—enabling fast, accurate speech-to-text for any workflow.

Supported Transcription Model Providers

Local Transcription Model Providers

Built-in (default)
Xenova Whisper
Fast, private Whisper-based transcription via Xenova.

Cloud Transcription Model Providers

OpenAI
OpenAI
Industry-leading Whisper Large-V3 and more for cloud STT.
Language ModelsVoice Chat (Hands‑Free)

MIT 2025 © RealTimeX, Inc.