---
title: ServiceNow-AI/Apriel-Voice-27B-preview
url: https://recentmodel.com/models/ServiceNow-AI/Apriel-Voice-27B-preview/
status: just landed
published: 2026-10-13T09:07:53Z
updated: 2026-10-30T11:19:53Z
source: https://huggingface.co/ServiceNow-AI/Apriel-Voice-27B-preview
---

# ServiceNow-AI/Apriel-Voice-27B-preview

Audio text to text model from ServiceNow-AI (HF pipeline tag; the card has no one-line description). 27B params. License: mit.


- **Org:** ServiceNow-AI
- **Released:** 2026-10-13
- **Status:** just landed
- **License:** mit (permissive)
- **Parameters:** 27.2B
- **Architecture:** AprielVoiceModel
- **Task:** audio-text-to-text · audio
- **Signal:** 44 HF likes · 96 downloads

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~19.6 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.2 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~57.8 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/ServiceNow-AI/Apriel-Voice-27B-preview)