PulseAugur
EN
LIVE 06:19:38

New GEPARD TTS model achieves 15x real-time speed for dialogue

By PulseAugur Editorial · [1 sources] ·

Researchers have developed GEPARD, a novel text-to-speech model designed for real-time dialogue applications. This model utilizes an LLM backbone for autoregressive speech generation and a neural codec for waveform decoding, enabling it to stream audio incrementally as text is processed. GEPARD is engineered to operate efficiently with standard LLM serving engines like vLLM, achieving a real-time factor of approximately 0.067 (15x faster than real-time) for single streams and significant aggregate speedups under concurrent usage. AI

IMPACT This model could significantly improve the responsiveness and naturalness of AI-powered conversational agents.

RANK_REASON Research paper detailing a new TTS model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New GEPARD TTS model achieves 15x real-time speed for dialogue

How we ranked this

Signal score
32 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper detailing a new TTS model. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Denis Pavlov, Ulanbek Abdurazakov, Nursultan Bakashov ·

    GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue

    arXiv:2609.04222v1 Announce Type: cross 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 backbon…

RELATED ENTITIES

RELATED TOPICS