Japanese TTS API for product and course narration — Audra

One OpenAI-compatible endpoint covers ten Essential languages — without juggling providers per locale. Not for realtime voice agents or cloning.

Who this is for

• Product teams localizing narration across EN, JA, ZH, ES, PT-BR, HI, FR, IT, DE, NL
• Docs and support orgs that need one TTS endpoint per language pack
• Builders who want BCP-47 language hints without juggling providers
• Anyone previewing locale-matched voices before hard-coding slugs

Languages on Essential

Prefer a voice slug that implies the locale; set language (BCP-47) only when the slug is ambiguous. Keep one locale per request — never mix languages in a single POST.

• Filter /voices and /compare by language before hard-coding production slugs
• Long localized docs → jobs API; short UI strings → sync /v2/speech
• Plus/Pro expand multilingual presets when Essential voices feel thin — see /pricing#engines

Example with a language hint

curl
curl https://audratalks.com/v2/speech \
  -H "Authorization: Bearer sk-live-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"audra-essential","text":"Bonjour — narration de documentation.","voice":"june","language":"fr-FR","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": "Bonjour — narration de documentation.",
        "voice": "june",
        "language": "fr-FR",
        "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: "Bonjour — narration de documentation.",
    voice: "june",
    language: "fr-FR",
    format: "mp3",
  }),
});

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

Next: preview voices on /voices. For engine multipliers see /pricing#engines; for voice A/B use /compare.

Cost sanity check

Want to hear a sample on your own script? Get an API key at /dashboard — 25k free characters, no card.

FAQ

Next steps

• Primary next step: preview voices on /voices
• A/B voices on /compare
• Honest matrices: /vs/elevenlabs and /vs/openai-tts
• Read next: /blog/multilingual-tts-api-10-languages
• Related: /migrate