> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. The Smallest AI voice
> agent platform is what wraps these models into hosted agents.

# Pulse Pro model card: diarization Capability removed; `eou_timeout_ms` range documented

Two small corrections on the Waves STT surface.

**Pulse Pro model card no longer claims speaker diarization.** The Capability block previously said "Multi-speaker identification with per-word speaker labels", which contradicted the API reference and the [Speaker diarization](/models/documentation/speech-to-text-pulse/features/diarization) page. Live: `POST /waves/v1/stt/?model=pulse-pro&diarize=true` returns a transcript-only response with no `speaker` fields on `words[]` and no `utterances[]`. The Capability is dropped from the card. Route diarization traffic to `?model=pulse`.

**`eou_timeout_ms` now carries `minimum: 100` and `maximum: 10000` on the streaming spec.** The Speech-to-Text WebSocket reference page dropped the range because the AsyncAPI schema on `stt-live-ws.yaml` (and the v4 override) only had a description. Both files now expose the accepted bounds so the rendered docs surface them alongside the field.