Editts: Score-based Editing For Controllable Text-to-speech

Abstract

We present EdiTTS, an off-the-shelf speech editing methodology based on score-based generative modeling for text-to-speech synthesis. EdiTTS allows for targeted, granular editing of audio, both in terms of content and pitch, without the need for any additional training, task-specific optimization, or architectural modifications to the score-based model backbone. Specifically, we apply coarse yet deliberate perturbations in the Gaussian prior space to induce desired behavior from the diffusion model while applying masks and softening kernels to ensure that iterative edits are applied only to the target region. Through listening tests and speech-to-text back transcription, we show that EdiTTS outperforms existing baselines and produces robust samples that satisfy user-imposed requirements.

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keytae2021editts

Related papers

• Editspeech: A Text Based Speech Editing System Using Partial Inference And Bidirectional Fusion (2021)9.92
• Fluenteditor: Text-based Speech Editing By Considering Acoustic And Prosody Consistency (2023)7.18
• Styletts: A Style-based Generative Model For Natural And Diverse Text-to-speech Synthesis (2022)10.97
• Edityourself: Audio-driven Generation And Manipulation Of Talking Head Videos With Diffusion Transformers (2026)0.00
• Rfm-editing: Rectified Flow Matching For Text-guided Audio Editing (2025)0.00
• Stable-tts: Stable Speaker-adaptive Text-to-speech Synthesis Via Prosody Prompting (2024)4.52
• Fluenteditor2: Text-based Speech Editing By Modeling Multi-scale Acoustic And Prosody Consistency (2024)3.95
• Pronunciation Editing For Finnish Speech Using Phonetic Posteriorgrams (2025)3.66