UK English TTS API: en-gb voices for British narration — Audra

British narration is not just an accent toggle: en-GB presets change rhythm, vowel length, and date/number reading conventions. Audra ships eight en-GB voices on Essential — the same OpenAI-compatible /v2/speech endpoint, just a locale-specific slug.

en-GB voice slugs on Essential

elise — calm RP, default pick for corporate explainers
arthur — warm male RP, matches UK documentary tone
lily and freya — lighter contemporary London/South-East reads
daniel — newsreader pacing for bulletins and IVR prompts
All eight en-GB slugs are on /voices — filter by language before hard-coding

UK-specific notes

Numbers and dates read British-style (e.g. 'the fifth of November') with en-GB slugs
Spot-check brand names — UK and US slugs can stress different syllables
Don't set language: en-GB on a US slug; pick the en-GB slug instead
For mixed UK/US audiences, keep one slug per channel — switching mid-series sounds like a host change

Example request in English (en-GB)

curl
curl https://audratalks.com/v2/speech \
  -H "Authorization: Bearer sk-live-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"audra-essential","text":"Welcome to this week's product update \u2014 here's what shipped for UK customers.","voice":"elise","language":"en-GB","format":"mp3"}' \
  --output out.mp3

Python
import requests

r = requests.post(
    "https://audratalks.com/v2/speech",
    headers={"Authorization": "Bearer sk-live-YOUR_KEY"},
    json={
        "model": "audra-essential",
        "text": "Welcome to this week's product update — here's what shipped for UK customers.",
        "voice": "elise",
        "language": "en-GB",
        "format": "mp3",
    },
    timeout=120,
)
r.raise_for_status()
open("out.mp3", "wb").write(r.content)

JavaScript
import { writeFile } from "node:fs/promises";

const res = await fetch("https://audratalks.com/v2/speech", {
  method: "POST",
  headers: {
    Authorization: "Bearer sk-live-YOUR_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "audra-essential",
    text: "Welcome to this week's product update — here's what shipped for UK customers.",
    voice: "elise",
    language: "en-GB",
    format: "mp3",
  }),
});

if (!res.ok) throw new Error(await res.text());
await writeFile("out.mp3", Buffer.from(await res.arrayBuffer()));

Hear elise or arthur on your own UK script — API key at /dashboard, 25k free characters, no card.

FAQ

How is en-GB different from en-US on Audra?

Different preset slugs with different prosody and number-reading conventions — not one voice with an accent flag. Choose the slug that matches your audience.

Can I mix UK and US voices in one series?

Technically yes (one voice per request), but listeners hear the switch as a host change. Pick one locale per series.

Do en-GB voices cost more?

No — all Essential voices are the same $25/1M characters before engine multipliers.

en-GB catalogue: /voices. Reading a full script? Use the jobs API for anything over 50k characters.