Pith. sign in

REVIEW 2 cited by

SpeakStream: Streaming Text-to-Speech with Interleaved Data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.19206 v1 pith:4TCX6I3D submitted 2025-05-25 cs.CL cs.LGcs.SDeess.AS

classification cs.CLcs.LGcs.SDeess.AS
keywords streaminglatencyspeakstreamconversationalsystemstextagentsdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete utterances, introduce unacceptable delays, even with optimized inference speeds, when coupled with streaming LLM outputs. This is particularly problematic for creating responsive conversational agents where low first-token latency is critical. In this paper, we present SpeakStream, a streaming TTS system that generates audio incrementally from streaming text using a decoder-only architecture. SpeakStream is trained using a next-step prediction loss on interleaved text-speech data. During inference, it generates speech incrementally while absorbing streaming input text, making it particularly suitable for cascaded conversational AI agents where an LLM streams text to a TTS system. Our experiments demonstrate that SpeakStream achieves state-of-the-art latency results in terms of first-token latency while maintaining the quality of non-streaming TTS systems.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    LyraV uses FDTC and SToP for per-frame incremental decoding to reach 98.29% video synchrony at 3.89 FPS while preserving general understanding.

  2. ChipChat: Low-Latency Cascaded Conversational Agent in MLX

    eess.AS 2025-08 conditional novelty 5.0 of 10

    ChipChat is a fully on-device cascaded voice agent that reports about 920 ms total latency using streaming ASR, a state-action LLM, streaming TTS, and a vocoder.

Pith tools