Skip to content
Preprint

TinyAudio: Compact and Efficient Text-to-Audio Generation for Low-Resource Deployment

Sep 2026 · 0 citations · 30 references
Computer Science Engineering

TL;DR

TinyAudio is introduced, a compact flow-matching-based TTA model for low-resource deployment that achieves competitive generation quality on AudioCaps and TTA-Bench and demonstrates a practical quality-footprint trade-off for low-resource TTA deployment.

Abstract

Text-to-audio (TTA) generation has advanced rapidly in generation quality and instruction following. However, representative systems often require around a billion parameters, limiting deployment on resource-constrained devices. This paper introduces TinyAudio, a compact flow-matching-based TTA model for low-resource deployment. At its core, TinyAudio uses TA-DiT, a 35M single-stream flow-matching Transformer. TinyAudio also includes TA-CLAP, a 32M audio-aligned text encoder, and TA-VAE, whose 20M decoder reconstructs 44.1 kHz audio from compressed latents. TinyAudio has only 87M parameters in total, over 90% fewer than representative billion-parameter pipelines, and uses 0.48 GB peak GPU memory. TinyAudio achieves competitive generation quality on AudioCaps and TTA-Bench. We further introduce TinyAudio-MF, a MeanFlow-accelerated model that enables real-time generation with a four-core CPU quota. Our results demonstrate a practical quality-footprint trade-off for low-resource TTA deployment.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding

Experiments show that ZipCodec substantially outperforms existing streaming codecs at comparable bitrates in both reconstruction and downstream tasks, while operating at a significantly lower frame rate.

Luca Della Libera, Cem Subakan, M. Ravanelli · 0 citations
#machine learning Preprint Sep 2026

Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement

Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent speech-enhancem...

Clément Laroche, R. Olsson · 0 citations
Preprint Sep 2026

X-Pred MeanFlow for Streaming Token-to-Mel Speech Decoding

X-Pred MeanFlow is proposed, a few-step streaming token-to-mel decoder that reparameterizes MeanFlow with mel-space prediction and introduces layer-selective block-wise attention to enable continuous chunk-wise generation with bounded context.

Han-Ke Xie, Xia-Ming Ren, Qi-Rui Zhan et al. · 0 citations
Preprint Sep 2026

RVQ Position Aware Speculative Decoding for On Device Text to Speech

This work proposes RVQ position aware speculative decoding for the MultiCodeDecoder, and delivers 2 to 2.2x speedup for RVQ token generation with Qwen3-TTS 0.6B on recent iPhone and Apple Silicon Mac devices.

Berkin Durmus, Eduardo Pacheco, Zach Nagengast et al. · 0 citations

IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence

We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid attention architecture with X-MTP, a lightweight shared-KV multi-token prediction design that eliminates per-depth KV-cache replay and employs a lightweight verification head for rollback-...

Chang-Di Yang, Feng-Quan Jiao, Hao-Chih Lin et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.