Skip to main content

​
1. Create an account and an API key

Sign up at speko.dev. Open Settings → API keys and click Create key. Copy the raw value — it is shown once and starts with sk_live_. 
export SPEKO_API_KEY=sk_live_xxx

​
2. Configure providers (optional)

Speko uses platform-managed provider credentials by default. To bring your own keys (BYOK), open Settings → Providers in the dashboard and paste each provider’s API key. Speko still picks the best provider per call; your keys are billed by the provider directly. See BYOK.

​
3. Make your first call

curl -X POST https://api.speko.dev/v1/transcribe \
  -H "Authorization: Bearer $SPEKO_API_KEY" \
  -H "Content-Type: audio/wav" \
  -H "x-speko-intent: {\"language\":\"en-US\",\"vertical\":\"general\"}" \
  --data-binary @call.wav
The response includes provider, model, confidence, and failoverCount so you can see what actually ran. Routing headers are also returned: X-Speko-Provider, X-Speko-Model, X-Speko-Failover-Count, X-Speko-Scores-Run-Id.

​
4. Pick your next path

Build a voice agent

Real-time STT → LLM → TTS pipeline with LiveKit.

Add voice to a browser app

@spekoai/client over WebRTC.

Use the one-shot APIs

/v1/transcribe, /v1/synthesize, /v1/complete for batch and server flows.

How routing decides

Intent, scoring, failover, constraints.