docs(whats-new): rewrite Vapi Voices item as v2 model upgrade

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: nick-vapi

fern/changelog/2026-06-01.mdx

@@ -2,7 +2,9 @@
 
 1. **xAI Speech-to-Text and Text-to-Speech**: xAI is now available as a transcriber (STT) and voice (TTS) provider for assistants.
 
-2. **New Vapi Voices**: Three new voices — Emma, Clara, and Nico — join the [Vapi Voices](https://docs.vapi.ai/providers/voice/vapi-voices) collection.
+2. **Upgraded Vapi Voices**: A new text-to-speech model powering [Vapi Voices](https://docs.vapi.ai/providers/voice/vapi-voices) makes them sound more authentic, human, and consistent — at ~50% lower cost.
+    - Available for Clara, Godfrey, Layla, Sid, Elliot, Savannah, Nico, Kai, Emma, Sagar, Neil, and Naina.
+    - Existing deployments don't change automatically — opt in by setting `version: 2` on the voice configuration via the API or Dashboard.
 
 3. **Pronunciation Dictionaries in the Dashboard**: The Assistants view now supports creating new [pronunciation dictionaries](https://docs.vapi.ai/assistants/pronunciation-dictionaries) directly from the dashboard.