# NousResearch/hermes-agent · WeChat/multi-gateway inbound voice STT fixes

## Open now

- 3 issues, 1 PR open on GitHub.
- #11686: \[Bug\]: Weixin inbound voice messages skip audio download when text hint exists
- #32196: Weixin(WeChat) voice messages in Silk format skip STT — russian transcription broken
- #42084: fix(gateway): convert WeChat Silk voice messages to WAV via pysilk for STT
- PR #42141: fix(weixin): convert Silk voice messages to WAV via pilk for STT

These issues and PRs address bugs in processing inbound voice messages across WeChat (Weixin) and other gateways, focusing on Silk-to-WAV conversion, STT routing, and cases where audio was skipped or mishandled when a text hint was present.

## TL;DR

- 10 member(s): 3 open issue(s), 1 closed issue(s), 1 open PR(s), 1 merged PR(s), 4 PR(s) closed without merging.
- A fix was merged to main in PR #73515. Verify it addresses your case.
- **Recommended:** read PR #73515 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `partially_resolved` · deciding PR(s): `pr-73515`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.20`: 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

- #11686: \[Bug\]: Weixin inbound voice messages skip audio download when text hint exists
- #32196: Weixin(WeChat) voice messages in Silk format skip STT — russian transcription broken
- #42084: fix(gateway): convert WeChat Silk voice messages to WAV via pysilk for STT

## Closed / duplicate issues

- #27300: WeChat voice messages use Tencent Cloud STT which garbles non-Chinese languages — should route through Hermes' own STT pipeline

## Prior & competing PRs

- **#73515: fix(gateway): inbound voice classification/routing for Feishu, DingTalk, LINE, QQ, Photon, WhatsApp, Weixin**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`; implication `superseded`
  - files: `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `contributors/emails/[redacted:email]`, `gateway/platforms/qqbot/adapter.py`, `gateway/platforms/weixin.py`, `gateway/run.py`, `plugins/platforms/dingtalk/adapter.py`, `plugins/platforms/feishu/adapter.py`, `plugins/platforms/line/adapter.py`, `plugins/platforms/photon/adapter.py`, `plugins/platforms/whatsapp/adapter.py`, `tests/gateway/test_dingtalk.py`, `tests/gateway/test_feishu.py`, `tests/gateway/test_feishu_voice_message_type.py`, `tests/gateway/test_line_plugin.py`, `tests/gateway/test_qqbot.py`, `tests/gateway/test_stt_config.py` (+6 more)
- **#11689: fix(weixin): keep inbound voice audio when text hint exists**. closed without merge
  - maintainer direction: category `silent_close`; implication `active`
- **#27316: fix(weixin): opt into local STT for inbound voice messages (#27300)**. closed without merge
  - maintainer direction: category `stale_abandoned`; implication `active`
- **#42141: fix(weixin): convert Silk voice messages to WAV via pilk for STT**. open
  - maintainer direction: category `wontfix_bydesign`; implication `wontfix`; refs `#31487`
  - files: `gateway/platforms/weixin.py`
- **#51924: fix(weixin): 5 WeChat bug fixes — voice STT, polling hang, msg truncation, session split, interrupt**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#51924`
- **#83763: fix(weixin): convert Silk voice messages to WAV via pilk for STT**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#42141`

## Fix status

- Merged to main in PR #73515 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-07-28`.
- Subsystem: `gateway`