← All products

Speech API · GA · v1.0

Voice, Talk, Speak, and Transcribe on Simon

Realtime voice, text-to-speech, and transcription — one API on Simon. Build voice agents and apps without stitching three vendors together.

RealtimeTTSTranscriptionUnified billing

WebSocket sessions · simon-says-* slugs · GA

Capabilities

Voice without vendor sprawl

Same keys, same usage logs, same billing as chat and vision — plus voice built into Ainslie out of the box.

Live

Realtime sessions

Low-latency voice conversations over WebSocket.

Slugs

TTS & transcription

simon-says-tts and simon-says-transcribe slugs.

Billing

Unified billing

Same keys and usage logs as chat and vision.

Ainslie

Ainslie built-in

Voice in the team workspace out of the box.