Перейти к содержимому
Audexum
Back

How do I get an API key and make my first call?

Audexum1 мин

Sign in, open Developer settings, create a key that starts with sk_live_, and send it as a Bearer token to POST https://audexum.com/api/synthesize. The free plan includes API access, and creating your first key adds 250 credits.

How do I get a key?

  • Sign in and verify your email.
  • Open Developer settings and create a key. It is shown once, so copy it right away.
  • Send it on every request as Authorization: Bearer sk_live_....

Revoke a key from the same page if it leaks. Restricted keys for the website Listen widget are created there too.

What does the first request look like?

curl -X POST https://audexum.com/api/synthesize -H "Authorization: Bearer sk_live_..." -H "Content-Type: application/json" -d '{"text": "Hello world"}' --output hello.wav

With no engine named, you get V3 Expressive on the voice Atlas. Useful fields are backend (v1, v2, v3 or v4), voice, lang, speed, format (wav, mp3, ogg or opus), stream (WAV from V1 and V2 only) and instruct for a style direction of up to 300 characters.

The full reference is in the API docs.

What are the limits and errors?

  • Text length: 5,000 characters per call, 15,000 on V1.
  • Rate: 60 requests per minute per key.
  • 401: missing or invalid key. 402: not enough credits, or a plan feature is locked. 429: too many requests. 503: busy, retry with backoff.
  • Transcription: POST /api/transcribe takes a file up to 25 MB and 600 seconds, at 200 credits per minute.

Credits and costs are the same as in Studio. See How do credits work? and Why did my generation fail with 'out of credits'?

Was this article helpful?
NextCan I use Audexum as an ElevenLabs or OpenAI TTS drop-in?

Still looking for answers?

Search every article, ask the assistant, or write to [email protected]. A person reads every email.