Speakr adds audio capture, webhooks, and LLM transcript tools
Speakr v0.9.0-alpha was announced. Speakr is a self-hosted audio transcription app that can record or upload audio and video, create speaker-labeled transcripts, and use the user’s own LLM to summarize or chat with them. The update adds system audio capture, multi-input recording, webhooks, recording stats, and a redesigned UI.
Key points
- Speakr is a self-hosted app for audio transcription.
- It can create speaker-labeled transcripts from recorded or uploaded audio and video.
- Users can summarize or chat with transcripts using their own LLM.
- Chrome or Edge on Windows and ChromeOS get full system audio capture, according to the post.
- Webhooks can send signed events for transcription, summaries, and recording lifecycle updates.
Quick term guide
- self-hosted
- Run on your own server instead of managed by another company.
- self-host
- To run a website, app, or service on your own server instead of using a hosted provider.
- transcription
- Automatically converting spoken words into a written text file during a meeting.
- transcript
- A full written record of everything spoken in a video
- transcripts
- Records of the messages and actions from a session with an AI tool.
- AI agents
- AI agents are AI tools that can carry out steps toward a goal, not just answer once.
- automated
- When a task is done by a machine or computer instead of a person.
- alpha release
- An early version that may still change or have problems.