Apriel Voice 27B Preview：一个支持语音、推理和工具使用的开源模型

Published on Oct 29

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Apriel Voice 27B Preview is an open speech-language model that integrates speech understanding, reasoning, and tool use within a shared backbone, achieving strong results on audio benchmarks through a two-stage training procedure with online distillation.

A capable voice assistant must do more than recognize words; it must understand requests, reason over context, sustain conversations, and act through tools. We present Apriel Voice 27B Preview, an open speech-language model that unifies these capabilities within a shared reasoning backbone while retaining text and image input modalities. Built on the post-trained Gemma 4 26B-A4B checkpoint, Apriel Voice directly processes speech and generates both responses and tool calls without requiring a separate dialogue model. We introduce a two-stage training procedure to adapt the model to speech. The first stage establishes the speech interface, while the second jointly adapts the projector and backbone through supervised fine-tuning, text replay, and source-dependent cross-entropy and forward Kullback--Leibler divergence supervision. Automatically constructed speech-conditioned dialogues provide conversational training data, while local teacher serving, overlapping teacher and student computation, and fused full-vocabulary losses enable efficient online distillation. In thinking mode, Apriel Voice achieves a score of 98.90 on Big Bench Audio, 81.13 on Speech-BFCL, and a task success rate of 65.51% on τ-Voice, with a mean latency of 1.91 seconds. It also achieves 51.27% English EVA accuracy and 74.13% experience pass@1. Finally, we deploy Apriel Voice 27B Preview on a custom serving platform to support interactive voice interactions.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.40738

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

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

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.40738 in a dataset README.md to link it from this page.

Spaces citing this paper 1

Collections including this paper 1