Where it fits
Speech synthesis
The Speech resource region and credential must match. APIFleet’s Azure adapter here is speech synthesis, not Azure-hosted realtime or transcription.
Configure the connection
Configure the Azure Speech credential and region, then select a voice name available in that region. Choose STT and LLM providers independently.
Assistant configuration fragment. Merge this into your assistant; select current model and voice IDs from your account before saving.
{
"pipeline_mode": "cascading",
"tts_provider": "azure",
"tts_voice": "YOUR_AZURE_VOICE_NAME"
}Keep provider secrets in workspace credentials. The public MCP provider matrix describes capabilities; it does not connect your provider account.
Test this boundary first
Check your expected language and regional pronunciation using the same script over browser and phone audio.
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.