Self-hosted alternatives to whisper
5 self-hosted AI Skills apps to use instead, best rated first.
Top picks
- C

claude-to-deerflow
Getclaude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code
Self-hosted
- O

open-notebook
Getopen-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O
Self-hosted
- R

Reactive Resume
GetReactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish
Open sourceSelf-hosted
- S

self-hosted-funnel-launch
GetSelf-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a
Self-hosted
- G

get-convex/convex-backend
GetConvex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca
Self-hosted
About whisper

whisper
OpenAI's general-purpose speech recognition model
whisper is an agent skill from the davila7 claude-code-templates collection, listed on skills.sh. It is a guide to Whisper, OpenAI's general-purpose multilingual speech recognition model. The skill covers speech-to-text transcription in 99 languages, translation to English, language identification, and transcription of noisy audio. The page lists uses such as podcast and video transcription, automated meeting notes, translation of foreign-language recordings and processing of multilingual audio. It also gives the model's own figures: a training set of 680,000 hours of audio, the 99 supported languages, and an MIT licence for the project. The listing mentions six model sizes, which let the user trade accuracy against speed and memory. The skill is for people who need text from recordings, such as journalists, researchers, students and teams that record meetings, and who want an agent to run the transcription for them with a model they control.
- Price
- Free
- Made by
- davila7
- Category
- AI Skills
- Website
- github.com/davila7/claude-code-templates/whisper