Realtime engine
The deepgram-agent voice engine
Deepgram's Voice Agent API runs the conversation as a single realtime session and drives ElevenLabs Turbo v2.5 for the voice itself. The synthesised text is not exposed, so its character count is inferred from the transcript and carries a small safety margin in the price.
Last updated
$0.1851per connected minute, including the $0.012 orchestration fee
What deepgram-agent runs, and what each part costs
A realtime engine hands the whole turn to one model, so the price is mostly that model’s units. The pipeline label is Deepgram Voice Agent.
| Stage | Model | Unit price | Per minute |
|---|---|---|---|
| Realtime model | deepgram/agent | $0.0018 per second | $0.1050 |
| Orchestration | wixzel/orchestration | $0.0120 per minute | $0.0120 |
Rounded up, never down. Where two models are listed for one stage the engine picks by language; the engine price above assumes the dearer path. All prices on the model price list.
Frequently asked questions
- What is the deepgram-agent voice engine?
- deepgram-agent is a realtime voice engine on Wixzel Phone. Deepgram's Voice Agent API runs the conversation as a single realtime session and drives ElevenLabs Turbo v2.5 for the voice itself. The synthesised text is not exposed, so its character count is inferred from the transcript and carries a small safety margin in the price.
- How much does the deepgram-agent engine cost per minute?
- $0.1851 per connected minute at typical speech rates, including the flat $0.012 per minute orchestration fee. The figure is generated from the price book the meter bills against and is rounded up, never down. Telephony runs over your own SIP trunk and is not included or marked up.
- Which models does the deepgram-agent engine use?
- deepgram-agent hands the whole turn to one realtime model:
deepgram/agent,elevenlabs/eleven_turbo_v2_5_via_agent. There is no separate speech-to-text or text-to-speech stage to configure. - Do I need my own deepgram account to use deepgram-agent?
- No. The provider accounts belong to Wixzel Phone. One
wv_live_…API key and a prepaid balance cover the deepgram-agent engine and every other engine; there are no provider keys to bring. - How do I use the deepgram-agent engine in a call?
- Set the agent's voice to
{"realtime": {"model": "deepgram/agent"}}when you create it withPOST /v1/agents, then place a call withPOST /v1/calls.GET /v1/engineslists what is available right now; an engine whose provider is degraded disappears from that list before calls start failing. - Is the deepgram-agent price per minute a flat rate?
- No. $0.1851 is what a typical minute adds up to. The meter charges per second of speech, per token and per character for the models that actually ran, plus the flat orchestration fee, and every micro-dollar is itemised in
GET /v1/usage/events. A quieter or shorter turn costs less; a long monologue costs more.