Speakr
Speakr is a personal, self-hosted web application designed for transcribing audio recordings (like meetings), generating concise summaries and titles, and interacting with the content through a chat interface. Keep all your meeting notes and insights securely on your own server.
Features
Properties
- Privacy focused
Features
- No Tracking
- Dark Mode
- Support for MarkDown
- Speech to text
- OpenAI integration
- Audio Summary
- AI-Powered
- AI Chatbot
- AI Summarization
- Drag and Drop
Tags
- AI Chat
- openai-api
- whisper-ai
- ai-transcription
Speakr News & Activities
Recent activities
rokartur added Speakr as alternative to BetterAudio- very_unfortunate updated Speakr
- very_unfortunate reviewed Speakr
Really solid. Well built, open source, competent dev, and pretty well documented. Good performance can be achieved.
Allows for local or remote endpoints (OpenAI API style compatibility).
Still a bit rough around the edges (especially for the documentation, where setup isn't really easy for beginners), but nearly everything works. It's impressive and beautiful!
Maoholguin added Speakr as alternative to Paraspeech
Maoholguin added Speakr as alternative to FLUID - AI Dictation
Speakr information
Developed by
Murtaza Nasir Licensing
Open Source (AGPL-3.0) and Free product.Alternatives
59 alternatives listedSupported Languages
- English
AlternativeTo Categories
AI Tools & Services, Audio & MusicGitHub repository
- 2,596 Stars
- 204 Forks
- 9 Open Issues
- Updated
What is Speakr?
Speakr is a personal, self-hosted web application designed for transcribing audio recordings (like meetings), generating concise summaries and titles, and interacting with the content through a chat interface. Keep all your meeting notes and insights securely on your own server.
Features:
Core Functionality:
- Audio Upload: Upload audio files (MP3, WAV, M4A, etc.) via drag-and-drop or file selection.
- Background Processing: Transcription and summarization happen in the background without blocking the UI.
- Transcription: Uses OpenAI-compatible Speech-to-Text (STT) APIs (configurable, e.g., self-hosted Whisper).
- AI Summarization & Titling: Generates concise titles and summaries using configurable LLMs via OpenAI-compatible APIs (like OpenRouter).
- Interactive Chat: Ask questions and interact with the transcription content using an AI model.
- Metadata Editing: Edit titles, participants, meeting dates, summaries, and notes associated with recordings.
User Features:
- Authentication: Secure user registration and login system.
- Account Management: Users can change their passwords.
- Recording Gallery: View, manage, and access all personal recordings.
- Dark Mode: Switch between light and dark themes.
Admin Features:
- Admin Dashboard: Central place for administration tasks (/admin).
- User Management: Add, edit, delete users, and grant/revoke admin privileges.
- System Statistics: View overall usage statistics (total users, recordings, storage, etc.).
Comments and Reviews
Really solid. Well built, open source, competent dev, and pretty well documented. Good performance can be achieved.
Allows for local or remote endpoints (OpenAI API style compatibility).
Still a bit rough around the edges (especially for the documentation, where setup isn't really easy for beginners), but nearly everything works. It's impressive and beautiful!