PhonePaint: Zero-Shot Frame-Synchronous Phoneme Editing
Examples of PhonePaint, Seed-VC*, a zero-shot voice conversion (VC) model, and VoiceCraft**, a zero-shot word-level editor.
No direct comparison with zero-shot open-source phone-based editing tools is possible as none exist***.
Edited phones are shown in
this color.
Cosine similarity between speaker embeddings of original and edited files obtained using
ECAPA_TDNN.
Project brief (PDF)
Audio clips were collected from YouTube. If you deem any of the clips to be your intellectual property and would like to have it removed, contact physicalchemistrytom{@g}mail.com (remove {}).
Unbatched inference × real-time with (warm startup) and without (cold startup) preloaded models on GTX Ti1080, averaged over demo files
| System | Cold-start × real-time | Warm-start × real-time |
|---|---|---|
| Seed-VC | 0.14 | 0.40 |
| VoiceCraft | 0.33 | 4.62 |
| PhonePaint (MAPS****) | 0.42 | 1.37 |
| PhonePaint (MFA****) | 0.24 | 0.31 |
* Largest Seed-VC v1 checkpoint (seed-uvit-whisper-base, 200M SVC); default settings with --f0-condition True and source = target
** VoiceCraft giga330M speech-editing model; default settings with contiguous
word-span infilling over the edited text
*** As of Aug 2026, no zero-shot open-source English phone editor is available; the closest
phoneme-level work is
PPG2Speech (Li et al., SSW 2025: Finnish, vowel-focused
single-phoneme edits; model and code)
**** Acoustic encoding & dynamic programming (MAPS)/HMM-GMM (MFA) run on CPU; MAPS scoring done on GPU
Audio failed to load. If you received this link privately, contact the sender.