Pith. sign in

REVIEW 8 cited by

MoonCast: High-Quality Zero-Shot Podcast Generation

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 2503.14345 v2 pith:5WGDOVNI submitted 2025-03-18 eess.AS cs.AIcs.CLcs.LGcs.SD

classification eess.AScs.AIcs.CLcs.LGcs.SD
keywords spontaneitygenerationhigh-qualitylongmooncastpodcastpodcastsspeech
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in text-to-speech synthesis have achieved notable success in generating high-quality short utterances for individual speakers. However, these systems still face challenges when extending their capabilities to long, multi-speaker, and spontaneous dialogues, typical of real-world scenarios such as podcasts. These limitations arise from two primary challenges: 1) long speech: podcasts typically span several minutes, exceeding the upper limit of most existing work; 2) spontaneity: podcasts are marked by their spontaneous, oral nature, which sharply contrasts with formal, written contexts; existing works often fall short in capturing this spontaneity. In this paper, we propose MoonCast, a solution for high-quality zero-shot podcast generation, aiming to synthesize natural podcast-style speech from text-only sources (e.g., stories, technical reports, news in TXT, PDF, or Web URL formats) using the voices of unseen speakers. To generate long audio, we adopt a long-context language model-based audio modeling approach utilizing large-scale long-context speech data. To enhance spontaneity, we utilize a podcast generation module to generate scripts with spontaneous details, which have been empirically shown to be as crucial as the text-to-speech modeling itself. Experiments demonstrate that MoonCast outperforms baselines, with particularly notable improvements in spontaneity and coherence.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks

    eess.AS 2026-08 conditional novelty 6.0 of 10

    SwanTale unifies instruction-driven and zero-shot speech and audio generation in one 48 kHz model, with a large captioning pipeline, and reports leading scores on several expressiveness and instruction-following benchmarks.

  2. On Improving Faithfulness of Podcasts from Documents

    cs.CL 2026-07 conditional novelty 6.0 of 10

    AI-generated podcasts often add unsupported claims; a turn-level detector plus rewrite pass improves measured faithfulness across five models and in- and out-of-domain documents.

  3. Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

    cs.SD 2026-06 unverdicted novelty 6.0 of 10

    ScenA generates multi-speaker audio scenes by conditioning a flow-matching foundation model on reference voices and natural language prompts, using a high-noise-biased timestep schedule to prevent reference shortcut.

  4. SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue

    eess.AS 2026-05 unverdicted novelty 6.0 of 10

    SwanVoice is a zero-shot TTS system for 1-4 speakers that reports higher richness and hierarchy scores than open-source baselines on monologue and dialogue tasks via mixed training and DiffusionNFT post-training.

  5. ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching

    eess.AS 2025-07 conditional novelty 6.0 of 10

    ZipVoice-Dialog is a flow-matching non-autoregressive model for zero-shot spoken dialogue generation that uses curriculum learning and speaker-turn embeddings, paired with a new 6.8k-hour OpenDialog dataset, and repor...

  6. Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning

    eess.AS 2026-04 unverdicted novelty 5.0 of 10

    A cascaded audio-prompting and ICL-based online RL method improves naturalness and expressivity in conversational TTS with reduced data needs.

  7. FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot

    cs.SD 2025-09 conditional novelty 5.0 of 10

    FireRedTTS-2 generates long multi-speaker conversations in a streaming, sentence-by-sentence way using a new low-rate speech tokenizer and a dual-transformer text-speech model.

  8. Kimi-Audio Technical Report

    eess.AS 2025-04 unverdicted novelty 5.0 of 10

    Kimi-Audio is an open-source audio foundation model that achieves state-of-the-art results on speech recognition, audio understanding, question answering, and conversation after pre-training on more than 13 million ho...

Pith tools