Bring your own SIP trunk

APIs for AI voice agents

One API key, one balance, every voice engine. No ElevenLabs key, no Deepgram key, no OpenRouter key — and no per-seat pricing. You are billed per second of what a call actually consumes.

Start building Read the docs

$ curl https://api.voice.wixzel.com/v1/calls \
    -H "Authorization: Bearer $WIXZEL_API_KEY" \
    -H "Idempotency-Key: $(uuidgen)" \
    -d '{
      "to": "+14155550100",
      "agent_id": "ag_01HXYZ"
    }'

{
  "object": "call",
  "status": "queued",
  "session_id": "sip-4f2a…",
  "cost_micros": null
}

# and when it ends:
"duration_seconds": 187,
"cost_micros": 271400  # $0.2714

Five vendor accounts, or one

A voice agent normally means separate contracts, keys, invoices and rate limits for speech-to-text, the model, and speech synthesis — each with its own failure mode and its own bill to reconcile.

Without Wixzel Voice

Accounts with Deepgram, OpenRouter and ElevenLabs
Three sets of keys to rotate and leak
Three invoices, none of them per-call
Your own media server, RTP pacing and barge-in logic

With Wixzel Voice

One key, scoped and rotatable
One prepaid balance, spent per second
Every charge itemised by component and call
Barge-in, endpointing and pacing already solved

Pick an engine, or compose one

Name the models you want and we wire them together — or pick a realtime model that does the whole conversation itself. Prices below are for a typical five-minute call, including our flat $0.012 per connected minute.

Engine	Pipeline	Per minute
classic	Deepgram + GPT-4o-mini + ElevenLabs	$0.055
sarvam	Sarvam — Indian languages end to end	$0.042
gemini-live	Gemini Live — native audio	$0.044
deepgram-agent	Deepgram Voice Agent	$0.151

Telephony is not included and not marked up — calls run over your own SIP trunk, so you keep your carrier rates and your carrier relationship.

  // compose the pipeline yourself
  "voice": {
    "stt": { "model": "deepgram/nova-3" },
    "llm": { "model": "openrouter/gpt-4o-mini" },
    "tts": { "model": "elevenlabs/eleven_turbo_v2_5" }
  }

  // or hand the whole turn to one model
  "voice": {
    "realtime": {
      "model": "google/gemini-live",
      "voice": "Charon"
    }
  }

Every charge is traceable to a second of audio

Credit is reserved before a call is placed and debited as it runs. Run low and the agent warns the caller before hanging up; run out and it says so rather than dropping the line mid-sentence.

$ curl .../v1/usage/events?session_id=sip-4f2a

stt         deepgram/nova-3        187s   $0.0336
llm         openrouter/gpt-4o-mini 8.2k   $0.0031
tts         elevenlabs/turbo_v2_5  1.4k   $0.0980
platform    orchestration          4 min  $0.0480
                                     ─────────
                                     $0.2714

No surprise invoices

Prepaid. You cannot be billed for more than you added.

Prices frozen per call

A call is priced at admission and finishes on those rates, so a price change never moves a meter mid-conversation.

Under-billed on our failures

If we crash mid-call you are charged for the seconds we can prove, not the amount we reserved.

Start with a curl

Create an account Read the quickstart