Self-hosted alternatives to openai-whisper-api

O

openai-whisper-api

OpenAI Audio Transcriptions API via curl

openai-whisper-api is an agent skill from the OpenClaw project, listed on skills.sh. It transcribes audio through OpenAI's /v1/audio/transcriptions endpoint with a bundled script, using gpt-4o-transcribe by default, or mini, diarize or whisper-1. You can point it at an OpenAI-compatible proxy or local gateway. Like every skill, it is a SKILL.md file of instructions the agent reads when the task calls for it, so the agent knows which commands to run and what to avoid. It is free and open source in the openclaw/openclaw repository on GitHub.