# Transcribe7 API > Speech-to-text API — real-time transcription over WebSocket and async file transcription over REST, with speaker > diarization, language identification and one-way / two-way translation. EUR 2 per audio hour, prepaid, billed per > second. REST: https://api.transcribe7.com/v1 · WebSocket: wss://api.transcribe7.com/transcribe-websocket · > Auth: `Authorization: Bearer t7_live_...` (servers) or temporary `t7_temp_...` keys (browsers / apps). Read the complete reference (one file, everything an integration needs) before writing code: ## Docs - [Complete API reference (Markdown, for AI assistants)](https://api.transcribe7.com/llms-full.txt): authentication, billing & limits, errors, real-time protocol, temporary keys, files, transcriptions, transcripts, webhooks, examples in Node.js / Python / C# / curl, integration rules - [Instructions for AI coding assistants](https://api.transcribe7.com/docs/ai.md): a short brief to paste into your AI assistant - [Human-readable docs](https://api.transcribe7.com/docs/): the same reference as a web page ## Platform - [Developer platform](https://platform.transcribe7.com): create API keys, projects, team members, credit, usage