# Cartesia — Announcing Sonic: a low‑latency voice model for lifelike speech

- Company: Cartesia (cartesia.ai)
- Announced: 2024-05-31
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.cartesia.ai/blog/sonic
- Record: https://forck.live/items/8031-announcing-sonic-a-low-latency-voice-model-for-lifelike-speech
- Subject: Sonic / Ink
- Models affected: Sonic

Cartesia released Sonic, a low-latency voice model that generates lifelike speech with a latency of 135ms, and includes a web playground and API.

## Evidence

Verbatim from https://www.cartesia.ai/blog/sonic:

> We’re releasing Sonic, our low-latency voice model that generates lifelike speech today. Sonic creates high quality lifelike speech for any voice with a model latency of 135ms—the fastest for a model of this class.

---

Record: https://forck.live/items/8031-announcing-sonic-a-low-latency-voice-model-for-lifelike-speech
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md