openrouter-stt

Convert audio speech to text transcripts using OpenRouter's speech-to-text API.

209|33|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/OpenRouterTeam/skills --skill openrouter-stt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openrouter-stt
Source: https://github.com/OpenRouterTeam/skills/tree/main/skills/openrouter-stt
Command: npx skills add https://github.com/OpenRouterTeam/skills --skill openrouter-stt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually transcribing audio recordings, meeting notes, or video audio is time-consuming and prone to human error. This skill eliminates that friction by providing a simple, reliable way to convert speech to text using OpenRouter's speech-to-text API.

Core Features & Use Cases

  • Multi-format audio support: Works with common audio formats including wav, mp3, flac, m4a, ogg, webm, and aac, with guidance to avoid format/byte mismatches.
  • Cross-language implementation examples: Includes ready-to-use code snippets for bash (curl + jq), TypeScript (fetch), and Python (requests) to handle the full transcription workflow.
  • Use case example: Transcribe a 30-minute customer support call recording to generate a searchable text transcript for quality review and note-taking.

Quick Start

Use the openrouter-stt skill to transcribe the audio file 'customer-call-recording.mp3' to text using the openai/whisper-large-v3 model.

Frequently Asked Questions about openrouter-stt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe an mp3 audio file to text using an API?

You can transcribe mp3 files by sending a base64 formatted audio payload to the OpenRouter speech-to-text API. This eliminates manual transcription effort and generates accurate text transcripts from your audio recordings.

Can I use Python to build a speech-to-text transcription workflow?

Yes, you can use Python to build a speech-to-text workflow by utilizing the requests library to handle the API integration. Ready-to-use code snippets are provided to manage the full transcription process for your audio files.

What audio formats are supported by the OpenRouter speech-to-text API?

The speech-to-text API supports common audio formats including wav, mp3, flac, m4a, ogg, webm, and aac. Proper formatting is required to avoid format and byte mismatches during the audio processing workflow.

Does this speech-to-text integration offer ready-to-use TypeScript code snippets?

Yes, the speech-to-text integration includes ready-to-use TypeScript code snippets using the fetch API. These examples handle the full transcription workflow, allowing developers to quickly implement ASR integration.

What is the best way to transcribe a 30-minute customer support call recording?

The best way to transcribe a 30-minute customer support call is to use a speech-to-text API with models like openai/whisper-large-v3. This generates a searchable text transcript for quality review and note-taking.