Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers
Apple has released Siri Expressive Voices, powered by a memory-efficient audio synthesis architecture called a detokenizer. This architecture converts semantic audio tokens from the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). It features a three-component design—a streaming encoder, a temporal decoder, and a depth decoder—that systematically decouples temporal and depth processing. A single reusable depth decoder with Diffusion Transformer (DiT)-style stage conditioning generates all RVQ levels autoregressively, replacing dedicated per-level decoders. Causal sliding window attention with fixed-window key-value caching yields constant memory complexity independent of sequence length. Deployed on the AMX, the detokenizer sustains roughly 10ms per generation step (about 16x faster than real time), with a peak runtime memory of only ~21MB and 329MB of on-device assets, enabling continuous streaming synthesis of 20–320 seconds of audio. The architecture is deployed in production as part of Siri Expressive Voices, running within AFM 3 Core Advanced (1-billion-parameter activation size) and improving Mean Opinion Score (MOS) by +0.28 overall (4.15 vs. 3.87) and by +0.42 on conversational speech (4.24 vs. 3.82) over the prior on-device TTS system.
content type paperpublished July 2026
Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers
AuthorsDongseong Hwang*, Prasanth Yadla*, Kaan Elgin*, Shifas Padinjaru Veettil, Sivanand Achanta, Dipjyoti Paul, Ramya Rasipuram, Tyler Johnson, Emad Soroush, Chung-Cheng Chiu, Zhifeng Chen
View publication
Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple’s most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design—a streaming encoder, a temporal decoder, and a depth decoder—that systematically decouples temporal and depth processing. A single reusable depth decoder with Diffusion Transformer (DiT)-style stage conditioning generates all RVQ levels autoregressively, replacing the dedicated per-level decoders of prior multi-decoder architectures, while causal sliding window attention with fixed-window key-value caching yields constant memory complexity independent of sequence length. Deployed on the AMX, the detokenizer sustains roughly 10ms per generation step—about 16x faster than real time—with a peak runtime memory of only ∼21MB and 329MB of on-device assets, enabling continuous streaming synthesis of 20–320 seconds of audio alongside the on-device foundation model. This constant, small footprint replaces the linear and quadratic memory scaling of conventional transformer- and GAN-based approaches. Comprehensive ablation studies validate the effectiveness of key architectural components, including DiT conditioning mechanisms, temporal lookahead processing, and unified depth decoding strategies. Audio quality assessment through phonetic discriminability analysis, perceptual quality metrics, and neural quality estimation confirms that the proposed architecture maintains synthesis fidelity while achieving computational efficiency gains over existing methodologies. The proposed architecture is deployed in production as part of Siri Expressive Voices, powering a voice overhaul with Pace and Expressivity customizations sliders in Apple Devices and support for custom assistant voices. Operating at a 1-billion-parameter activation size within AFM 3 Core Advanced, it improves Mean Opinion Score (MOS) by +0.28 overall (4.15 vs. 3.87) and by +0.42 on conversational speech (4.24 vs. 3.82) over the prior on-device text-to-speech system.
- Equal contribution
Introducing the Third Generation of Apple’s Foundation Models
June 8, 2026
Our next generation of Apple Intelligence is centered around our users, integrated deeply into our operating systems, and powered by a bold new architecture with privacy at its core.
At the heart of this architecture is our third generation of Apple Foundation Models (AFM), a family of five foundation models custom-built in collaboration with Google. These span from on-device models to server-based models running on Private Cloud Compute…
Read more
Voice Trigger System for Siri
August 11, 2023research area Speech and Natural Language Processing
A growing number of consumer devices, including smart speakers, headphones, and watches, use speech as the primary means of user input. As a result, voice trigger detection systems—a mechanism that uses voice recognition technology to control access to a particular device or feature—have become an important component of the user interaction pipeline as they signal the start of an interaction between the user and a device. Since these systems are deployed entirely on-device, several considerations inform their design, like privacy, latency, accuracy, and power consumption.
Read more