# NousResearch/hermes-agent · Deduplicating audio before speech-to-text processing

## Open now

- 1 issue, 1 PR open on GitHub.
- #91513: Telegram can transcribe the same replied-to voice twice via distinct cache paths
- PR #91518: fix(gateway): dedupe identical audio before STT

These items address a bug where the same audio content could be transcribed multiple times through distinct cache paths. The work involves deduplicating STT input by content rather than relying solely on cache path identity.

## TL;DR

- 3 member(s): 1 open issue(s), 0 closed issue(s), 1 open PR(s), 0 merged PR(s), 1 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

- #91513: Telegram can transcribe the same replied-to voice twice via distinct cache paths

## Prior & competing PRs

- **#91515: fix(gateway): dedup STT input by content, not just cache path**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#91518`
- **#91518: fix(gateway): dedupe identical audio before STT**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#91513`
  - files: `gateway/run.py`, `tests/gateway/test_stt_config.py`

## Fix status

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