---
title: Convert Speech to Text API
slug: speech-to-text
url: https://apyverse.com/apyhub/service/speech-to-text
provider: ApyHub
categories: [Artificial Intelligence, Audio Processing]
auth: api_key
---

# Convert Speech to Text API

Transcribe WAV audio from a URL or uploaded file using a language locale like en-US. Returns the transcript as plain text in data.

## Endpoints

| Method | Path | Description | Atoms |
| --- | --- | --- | --- |
| POST | `stt/url` | What it does Transcribes a WAV audio file from a URL and returns the transcription as text. The req… | 750 |
| POST | `stt/file` | What it does Transcribes a WAV audio file into text. You send the audio file and the Azure locale t… | 750 |

## About

## What it does
Speech to Text transcribes WAV audio into plain text. Send either a public WAV URL or a binary WAV file, along with the language locale, and get the transcript back in the `data` field.

Use the `/url` endpoint when your audio is already hosted, or `/file` when you’re uploading audio directly from your app. Both endpoints accept a `language` value such as `en-US`, which helps the transcription match the spoken language more accurately.

The response is intentionally simple: a single text string containing the transcription. That makes it easy to store, search, display, or pass into downstream workflows like call-note generation, subtitle creation, meeting indexing, or voice-command processing.

If you need a lightweight way to turn WAV speech into text without managing your own speech model pipeline, Speech to Text gives you a direct request-and-response interface.

## Usage

Authenticate with an ApyHub API key in the `apy-token` header.
Full docs and a live playground: https://apyverse.com/apyhub/service/speech-to-text