OpenRouter Audio Transcription
Transcribe audio files using OpenRouter's chat completions API with input_audio content type. Supports any audio-capable model including Google Gemini and OpenAI GPT-4o. Automatically converts audio to WAV format, handles base64 encoding, and extracts transcripts with customizable prompts.
🚀 Instantly convert audio files into text using OpenRouter's audio-capable models. Simply point the script at your audio file (M4A, OGG, WAV, etc.), and it handles the rest—converting to the right format, sending to the API, and returning a clean transcript. Works with any audio model available on OpenRouter.
💡 Perfect for transcribing interviews, meetings, voice notes, and podcasts without manual typing. Customize the output with speaker labels, save directly to files, and track usage through your OpenRouter dashboard. Great for content creators, researchers, and anyone drowning in audio files.
✨ No complex setup needed—just set your API key and run. The script intelligently handles large files and format conversions behind the scenes, so you focus on what matters.
Requirements
Valid OpenRouter API key for accessing audio-capable models