🚀 AnythingLLM v1.16.1 is live! Update now →

AnythingLLM Docs

(opens in a new tab)Discord (opens in a new tab)

▲ Home
AnythingLLM Roadmap
Getting Started
Introduction
Chat Interface overview
Other configurations
AnythingLLM Desktop Pro
Why AnythingLLM Pro?
Getting Your Pro Key
Managing Your Subscription
Magic Echo
Magic Beacon
Magic Tab
AnythingLLM Community Hub
What is the Community Hub?
Importing an item
Uploading an item
FAQ
Installation Guides
- Overview
- System Requirements
- Install for MacOS
- Install for Windows
- Install for Linux
- Desktop FAQ
- Update AnythingLLM
- Where is my data stored?
- Debugging & Logs
- Uninstall AnythingLLM
- Legal & Privacy
- Privacy Policy
- Terms of Use
- Overview
- Limitations
- 502 Error on AnythingLLM Hosted
- Terms & Conditions
- Terms & Conditions
- Privacy Policy
- Introduction
- Legal & Privacy
- Terms of Service
- Privacy Policy
Guides
- What is the Model Router?
- Setting up a Model Router
Importing custom models
- Install the AnythingLLM Browser Extension
- Introduction
- Features
- Introduction
- Features
- Telegram
Frequently Asked Questions
- Attaching vs RAG
- RAG in AnythingLLM
AI Agent not using tools!
Ollama Connection Debugging
Fetch failed error on embed
Manual QNN Model Download
More
Contribute
Support

On This Page

Supported Transcription Model Providers
Local Transcription Model Providers
Cloud Transcription Model Providers

Feature Overview

Speech to Text (STT)

AnythingLLM Transcription Models

Transcription Models

AnythingLLM supports custom audio transcription providers.

Supported Transcription Model Providers

Local Transcription Model Providers

AnythingLLM Built-in (Xenova)

Built-in (Xenova)→

Cloud Transcription Model Providers

OpenAI

Text to Speech (TTS)Image Generation

MIT 2026 © Mintplex Labs.