Loquela Remote

Loquela Remote turns English audio into text. It has two ways in:

• an API that follows OpenAI's transcription format, so OpenAI's SDKs work once you change the base URL;
• an MCP server for Claude, ChatGPT, Cursor and other AI assistants (MCP).

It is for customers in the United States, and it works with English audio only. Recordings are held in memory while they are transcribed, then erased; How your audio is handled explains each step. Plans and prices are on the pricing page.

Quick start

Create an API key on your account page. Keys start with lqr_. Send audio to the transcription endpoint with the key as a bearer token.

curl

curl https://api.getloquela.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $LOQUELA_API_KEY" \
  -F file=@meeting.m4a \
  -F model=loquela-remote-beta

Python

from openai import OpenAI

client = OpenAI(base_url="https://api.getloquela.com/v1", api_key="lqr_...")
with open("meeting.m4a", "rb") as f:
    result = client.audio.transcriptions.create(
        model="loquela-remote-beta",
        file=f,
        response_format="verbose_json",
        timestamp_granularities=["word"],
    )
print(result.text)

JavaScript

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.getloquela.com/v1", apiKey: "lqr_..." });
const result = await client.audio.transcriptions.create({
  model: "loquela-remote-beta",
  file: fs.createReadStream("meeting.m4a"),
});
console.log(result.text);

Next: every field of the transcription request, the response formats, and the limits.