titleApriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use
authorsAman Tiwari, Akshay Kalkunte, Akintunde Oladipo, Jash Shah, Tara Bogavelli, Hoang Nguyen, Nishanth Madhusudhan, Vishal Juneja, Sridhar Nemala, Srinivas Sunkara, Sathwik Tejaswi Madhusudhan, Shruthan Radhakrishna, Masoud Hashemi, Kelechi Ogueji, Khalil Slimi, Saloni Mittal, Pulkit Pattnaik, Shashank Maiya, Dhruv Jhamb, Esakkivel Esakkiraja, Katrina Stankiewicz, Gabrielle Gauthier Melançon, Fanny Riols, Amit Saha, Lakshmi Sirisha Chodisetty, Nitin Aggarwal, Anil Madamala, Sagar Davasam, Segan Subramanian, Vikas Yadav, Sai Rajeswar Mudumba
date2026-10-29
venuearXiv (preprint, not peer reviewed)
idarXiv:2610.40738
affiliationServiceNow-AI
upvotes33 (Hugging Face Daily Papers, 2026-11-03)
linksabs pdf hf
abstractA 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.

cite

@misc{tiwari2026apriel,
  title={Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use},
  author={Aman Tiwari and Akshay Kalkunte and Akintunde Oladipo and Jash Shah and Tara Bogavelli and Hoang Nguyen and Nishanth Madhusudhan and Vishal Juneja and Sridhar Nemala and Srinivas Sunkara and Sathwik Tejaswi Madhusudhan and Shruthan Radhakrishna and Masoud Hashemi and Kelechi Ogueji and Khalil Slimi and Saloni Mittal and Pulkit Pattnaik and Shashank Maiya and Dhruv Jhamb and Esakkivel Esakkiraja and Katrina Stankiewicz and Gabrielle Gauthier Melançon and Fanny Riols and Amit Saha and Lakshmi Sirisha Chodisetty and Nitin Aggarwal and Anil Madamala and Sagar Davasam and Segan Subramanian and Vikas Yadav and Sai Rajeswar Mudumba},
  year={2026},
  eprint={2610.40738},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2610.40738}
}