German TTS API for documentation and training audio — Audra

German is where batch pipelines earn their money: long compound nouns, technical documentation, and compliance-grade consistency. Five de voices on Essential handle it at $25/1M characters — greta for neutral documentation, klaus for corporate e-learning.

German voice slugs on Essential

• greta — neutral Hochdeutsch, safest default for docs and SOPs
• klaus — measured male read for compliance and training
• anke, martin, victoria — alternate pacing/gender for course variety
• All five de slugs at /voices; A/B on /compare

German-specific pitfalls

• Compound nouns: hyphenate novel compounds (Rendering-Warteschlange) to keep stress predictable
• Umlauts are fine in UTF-8 input — never transliterate (ae/oe/ue); the voices read them correctly
• Long docs: chunk at sentence boundaries and use the jobs API over 50k characters
• Formality: pick Sie or du per voice and keep it consistent across a whole course

Example request in German (de-DE)

curl
curl https://audratalks.com/v2/speech \
  -H "Authorization: Bearer sk-live-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"audra-essential","text":"Willkommen zur dritten Lektion: In diesem Kapitel behandeln wir die Rendering-Warteschlange.","voice":"greta","language":"de-DE","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": 'Willkommen zur dritten Lektion: In diesem Kapitel behandeln wir die Rendering-Warteschlange.',
        "voice": "greta",
        "language": "de-DE",
        "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: 'Willkommen zur dritten Lektion: In diesem Kapitel behandeln wir die Rendering-Warteschlange.',
    voice: "greta",
    language: "de-DE",
    format: "mp3",
  }),
});

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

Run a real German manual through greta — 25k free characters with an API key at /dashboard.

FAQ

Pronunciation previewing: /docs (phonemize endpoint). Cost modelling for German volume: /calc.