# Gradium — Why we built the fastest robust TTS model

- Company: Gradium (gradium.ai)
- Announced: 2026-10-01
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://gradium.ai/blog/fastest-robust-tts-model
- Record: https://forck.live/items/18300-why-we-built-the-fastest-robust-tts-model
- Subject: Gradium TTS / Phonon
- Models affected: Gradium's latest Text-to-Speech model, Eleven v4 Turbo

Gradium released a new Text-to-Speech model with 50ms first-chunk latency, which it claims is the lowest among frontier TTS models. The model beats Eleven v4 Turbo on latency while improving naturalness and expressivity across all languages, and retains handling of hard cases like phone numbers and alphanumeric text. It is now the default model for Gradium's API and studio, out of beta.

## Evidence

Verbatim from https://gradium.ai/blog/fastest-robust-tts-model:

> Our latest Text-to-Speech model takes around 50ms for the first audio chunk to arrive. These are the lowest latency figures out there among frontier TTS models.

---

Record: https://forck.live/items/18300-why-we-built-the-fastest-robust-tts-model
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md