# What changed in piper-tts

> 15 changes in piper-tts 1 from its official release notes, upgrade guides and advisories: 2 breaking, 11 new APIs and options. Each one cited. Sources checked 2026-10-27. HTML: https://unstale.sh/pypi/piper-tts/

To see which of these apply to a repository, run `npx @unstale/cli init` in it.

## piper-tts 1

### Breaking changes

- Run the g2pW model through piper.g2pw_onnx instead of g2pw.api; the model runs under onnxruntime without the prior torch-based batching. (1.6.1) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.6.1)
- The zh extra no longer installs torch or requests, reducing its installed dependencies. (1.6.1) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.6.1)

### New APIs and options

- Set this training option to `thai` to use the Thai phonemizer. (1.8.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.8.0)
- Set this voice configuration field to `thai` to use the Thai phonemizer for synthesis. (1.8.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.8.0)
- Adds a setup command option for Thai. (1.8.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.8.0)
- Adds a `th` extra for installing the Thai phonemizer dependency. (1.8.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.8.0)
- Adds TLTK-based Thai word segmentation and tone-aware phonemization; Thai voices remain compatible with the IPA-based (espeak) warmstart. (1.8.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.8.0)
- Use `--data.phoneme_type japanese` for training with the Japanese phonemizer. (1.7.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.7.0)
- Adds a ja extra with an OpenJTalk-based Japanese phonemizer using pyopenjtalk-plus. (1.7.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.7.0)
- Set `phoneme_type` to `japanese` in a voice config to synthesize with the Japanese phonemizer. (1.7.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.7.0)
- Adds `piper_create_options` to the libpiper API. (1.7.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.7.0)
- Adds `piper_create_with_options()` to libpiper; `piper_create()` remains as a wrapper for ABI compatibility. (1.7.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.7.0)
- Adds a setup command option for Japanese. (1.7.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.7.0)

### Performance

- g2pW runs 1.5–2x faster because it no longer forks DataLoader worker processes on every call. (1.6.1) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.6.1)

### Fixes and other changes

- Parses full-context labels for pitch accent and maps them to IPA, keeping Japanese voices compatible with IPA-based (espeak) warmstart. (1.7.0) — [release notes](https://github.com/OHF-Voice/piper1-gpl/releases/tag/v1.7.0)