Where it fits
Transcription · Speech synthesis
A transcription model is not a voice ID. Provider support for languages and models varies by endpoint.
Configure the connection
Choose Deepgram for STT, TTS or both. Select the STT model/language and TTS voice independently; APIFleet routes Aura and Flux voice families to their respective endpoints.
Assistant configuration fragment. Merge this into your assistant; select current model and voice IDs from your account before saving.
{
"pipeline_mode": "cascading",
"stt_provider": "deepgram",
"tts_provider": "deepgram"
}Keep provider secrets in workspace credentials. The public MCP provider matrix describes capabilities; it does not connect your provider account.
Test this boundary first
Read back names, dates and phone numbers, then interrupt mid-sentence. Check both final transcript accuracy and pronunciation.
Save a known working configuration and move one test route first. Inspect the call log before increasing traffic. Follow the staged migration guide.
Understand the bill
APIFleet adds $0.03 per connected AI minute, billed per second. Provider and carrier usage are additional. With your own keys, provider charges go directly to the provider. No monthly subscription or free call credits; prepaid top-ups start at $10.