APIFleet Sign in

Soniox.
In your voice stack.

Connect the implemented Soniox speech output adapter to a cascading assistant.

Where it fits

Speech synthesis

This APIFleet integration is TTS. It does not imply that every API offered by Soniox is exposed in the platform.

Configure the connection

Choose Soniox in the TTS stage and a voice supported by your account. Configure transcription independently with a supported APIFleet STT adapter.

Assistant configuration fragment. Merge this into your assistant; select current model and voice IDs from your account before saving.

{
  "pipeline_mode": "cascading",
  "tts_provider": "soniox",
  "tts_voice": "YOUR_SONIOX_VOICE_ID"
}

Keep provider secrets in workspace credentials. The public MCP provider matrix describes capabilities; it does not connect your provider account.

Test this boundary first

Try multilingual names and a continuous exchange with interruptions. Inspect synthesis failures separately from transcription errors.

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.

Calculate your scenario · Soniox documentation

Bring your next conversation.

Explore the API, or sign in to your existing workspace. New workspace access is currently limited; contact us to discuss your project.