Skip to main content

Quickstart

Make your first VocaBusta Voice API call in five minutes.

1. Get an API key​

  1. Sign in at satryx.ai and open Account → API keys (satryx.ai/account/api-keys).
  2. Click New key, name it (e.g. local-dev), pick Test or Live, and copy it. The key (satryx_live_… / satryx_test_…) is shown once — store it in a secret manager, never in client-side code or git.
  3. Make sure VocaBusta is active on your account. The voice generation endpoints are gated behind the VocaBusta subscription — manage it in Billing. Without it, generation calls return 403.

Export your key so the snippets below pick it up:

export SATRYX_API_KEY="satryx_live_…"

2. Synthesize speech​

cURL​

curl https://api.satryx.ai/voice/tts \
  -H "Authorization: Bearer $SATRYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "How far? Welcome to VocaBusta.",
    "voice_id": "vocabusta_pcm_female"
  }' \
  --output hello.wav

The response body is the raw WAV audio. Synthesis metadata (duration, character count, sample rate) comes back in the X-Vox-Metadata response header as JSON.

TypeScript / Node​

const res = await fetch("https://api.satryx.ai/voice/tts", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.SATRYX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    text: "How far? Welcome to VocaBusta.",
    voice_id: "vocabusta_pcm_female",
  }),
});
if (!res.ok) throw new Error(await res.text());

const meta = JSON.parse(res.headers.get("X-Vox-Metadata") ?? "{}");
const audio = Buffer.from(await res.arrayBuffer());
await require("node:fs/promises").writeFile("hello.wav", audio);
console.log(`Wrote ${audio.length} bytes — ${meta.duration_seconds}s`);

Python​

import os, json, requests

res = requests.post(
    "https://api.satryx.ai/voice/tts",
    headers={"Authorization": f"Bearer {os.environ['SATRYX_API_KEY']}"},
    json={"text": "How far? Welcome to VocaBusta.", "voice_id": "vocabusta_pcm_female"},
)
res.raise_for_status()

meta = json.loads(res.headers.get("X-Vox-Metadata", "{}"))
open("hello.wav", "wb").write(res.content)
print(f"Wrote {len(res.content)} bytes — {meta.get('duration_seconds')}s")

3. Pick a voice​

List the catalog to discover voice IDs for each language and gender:

curl https://api.satryx.ai/voice/voices \
  -H "Authorization: Bearer $SATRYX_API_KEY"

Each entry has an id (e.g. vocabusta_yo_male), a language, a gender and a preview_url. Pass the id as voice_id to /voice/tts. See Voices & languages for the full roster.

Next​