GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Electrical Engineering and Systems Science > Audio and Speech Processing
arXiv:2609.04222 (eess)
[Submitted on 4 Jul 2026]
Title:GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue
View a PDF of the paper titled GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue, by Denis Pavlov and 2 other authors
View PDF
HTML (experimental)
Abstract:We present GEPARD (Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue), a streaming text-to-speech model for real-time spoken dialogue. GEPARD generates speech autoregressively with an LLM backbone - text and audio embeddings are trained together in a single decoder-only model - and decodes it to a waveform with an FSQ-based neural codec, streaming audio chunk-by-chunk as text arrives.
Our central goal is a TTS architecture served by a standard LLM engine (vLLM) without modifying its compute kernels. This defines the overarching design principle: the backbone is a standard full-attention transformer, while all non-trivial auxiliary mechanisms - zero-shot voice cloning, text augmentation, and classifier-free guidance - are moved out of the autoregressive decode loop into prefill, or distilled directly into the weights.
On streaming end-to-end inference, a single stream reaches a Real-Time Factor of about 0.067 (roughly 15x faster than real-time); under 256 concurrent streams the system reaches an aggregate speedup of about 204x on a single server-class GPU. We detail: (1) system-level solutions for vLLM-native serving; (2) the "short register" (1-2 word) failure mode of autoregressive speech decoders, with diagnostic probes and a mitigation; and (3) distillation of two-pass classifier-free guidance over text into single-pass weights via Direct Preference Optimization (DPO).
| Comments: | Technical Report. 37 pages, 11 figures, Demo samples, code, and open weights: this https URL ; this https URL . Affiliation: Nineninesix, Inc |
| Subjects: | Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD) |
| Cite as: | arXiv:2609.04222 [eess.AS] |
| (or arXiv:2609.04222v1 [eess.AS] for this version) | |
| https://doi.org/10.48550/arXiv.2609.04222
arXiv-issued DOI via DataCite
|
Submission history
From: Ulanbek Abdurazakov Mr [view email][v1] Sat, 4 Jul 2026 13:56:27 UTC (1,265 KB)
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue, by Denis Pavlov and 2 other authors
Current browse context:
eess.AS
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.