Transcribe audio files to text via OpenRouter API with Gemini or GPT-4o.
npx skills add https://github.com/delorenj/00_ceiling --skill openrouter-transcribe
Please help me install this Agent Skill. Skill: openrouter-transcribe Source: https://github.com/delorenj/00_ceiling/tree/main/openrouter-transcribe Command: npx skills add https://github.com/delorenj/00_ceiling --skill openrouter-transcribe
This Skill automates the transcription of audio files into text, making spoken content searchable and usable for various applications.
Transcribe the audio file located at /path/to/audio.m4a using the default model.
High-intent search queries and answers about installing and using this skill.
You can transcribe audio files into text by sending them to the OpenRouter API. This Skill handles audio conversion, base64 encoding, and API interaction to generate the transcript.
Transcribing M4A or OGG voice memos is handled by converting the audio with ffmpeg, encoding it to base64, and passing it to an AI model via OpenRouter for text extraction.
This Skill supports various audio-capable AI models for speech-to-text via OpenRouter, including Gemini and GPT-4o, allowing you to choose the model that fits your needs.
Yes, you need curl, ffmpeg, base64, and jq installed. ffmpeg processes the audio files, while curl, base64, and jq handle API requests, encoding, and parsing the JSON response.
Yes, you can use custom instructions for audio transcription. The Skill supports custom prompts alongside audio-capable models like Gemini and GPT-4o to guide the output.
huggingfaceCreate reusable scripts for Hugging Face API data processing and retrieval.
hmzainjamilConvert audio and video recordings into transcripts, subtitles, and meeting notes.
pramudityadTranscribe audio files to plain text using the Groq Whisper API.
lemonlqfTranscribe and translate audio and video files into text or subtitles using the Whisper CLI.
