# NousResearch/hermes-agent · TTS paragraph pause handling fix

## Open now

- 1 issue, 2 PRs open on GitHub.
- #103103: Piper TTS: no pauses at paragraph breaks — whitespace flattened before synthesis
- PR #103130: fix: paragraph pauses for local TTS (piper/kittentts/neutts)
- PR #106252: fix(tts): preserve local paragraph pauses as explicit speech segments

These issues and pull requests concern paragraph-level pauses being lost or flattened during local TTS synthesis (Piper, KittenTTS, NeuTTS). The work involves preserving explicit pause segments so paragraph breaks produce audible pauses in speech output.

## TL;DR

- 3 member(s): 1 open issue(s), 0 closed issue(s), 2 open PR(s), 0 merged PR(s), 0 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.67`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #103103: Piper TTS: no pauses at paragraph breaks — whitespace flattened before synthesis

## Prior & competing PRs

- **#103130: fix: paragraph pauses for local TTS (piper/kittentts/neutts)**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#103103`
  - files: `tests/tools/test_tts_paragraph_pauses.py`, `tests/tools/test_tts_prepare_spoken.py`, `tools/tts_text_normalize.py`, `tools/tts_tool.py`, `tools/tts_tool_local.py`
- **#106252: fix(tts): preserve local paragraph pauses as explicit speech segments**. open
  - maintainer direction: category `wontfix_bydesign`; implication `wontfix`; refs `#106252`
  - files: `gateway/platforms/base.py`, `hermes_cli/cli_voice_mixin.py`, `hermes_cli/config_defaults.py`, `hermes_cli/voice.py`, `tests/tools/test_tts_paragraph_segments.py`, `tools/neutts_synth.py`, `tools/tts_text_normalize.py`, `tools/tts_tool.py`, `tools/tts_tool_local.py`, `tools/tts_tool_segments.py`, `website/docs/user-guide/features/tts.md`

## Fix status

- No merged fix on record.
- Subsystem: `agent`