# NousResearch/hermes-agent · Voice conversation timing and transcription fixes

## Open now

- 1 issue, 3 PRs open on GitHub.
- #94462: Discord voice mode has extreme latency or poor STT accuracy
- PR #110005: fix(discord): pause the voice receiver during mixer-path speech playback
- PR #110018: fix(gateway): send the voice-turn text before TTS playback
- PR #111090: feat(discord): add explicit transcription modes with bounded live lifecycle

These issues and pull requests address latency, speech-to-text accuracy, and lifecycle management problems in voice conversation mode, including fixes for turn timing, TTS/STT ordering, and receiver pausing during playback. A mobile browser voice conversation feature is also included.

## TL;DR

- 6 member(s): 1 open issue(s), 0 closed issue(s), 3 open PR(s), 0 merged PR(s), 2 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.33`: 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

- #94462: Discord voice mode has extreme latency or poor STT accuracy

## Prior & competing PRs

- **#95180: fix(desktop): isolate voice turn lifetimes**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `bee79171eacf6eb810a208ec8d3154a8891bb2e0`, `#94462`, `#77111`, `#95193`, `#95191`, `#95147`, `#95147`, `#95193`, `#94462`, `#95147`, `#101034`, `#95193`, `#95191`, `#98105`, `#94113`, `#106640`, `#94462`, `#95147`, `#95193`, `#98105`
- **#95193: feat(web): add mobile browser voice conversation**. closed without merge
  - maintainer direction: category `stale_abandoned`; implication `active`; refs `65539bc3361faf7afca31872db38eae70754052b`, `#94462`, `#95191`, `#95147`, `#101034`, `#95180`, `#98105`, `#95191`, `#95191`, `#94462`
- **#110005: fix(discord): pause the voice receiver during mixer-path speech playback**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#111090`
  - files: `plugins/platforms/discord/adapter.py`, `tests/gateway/test_discord_voice_mixer.py`
- **#110018: fix(gateway): send the voice-turn text before TTS playback**. open
  - maintainer direction: category `wontfix_bydesign`; implication `wontfix`; refs `#110284`, `#111090`, `#110005`
  - files: `gateway/platforms/base.py`, `tests/gateway/test_base_auto_tts_output_format.py`
- **#111090: feat(discord): add explicit transcription modes with bounded live lifecycle**. open
  - maintainer direction: category `merged_via`; implication `superseded`; refs `a55dbe67c62d748ad59c45f7cc83a25c94b3f69e`, `89cc2bbaae6acdbf956791210e52b21d7edfd159`, `679cb9ed85ff94327d87a3934d4d2fc6f69619a8`, `6f55860cb3a0ab14b9532a4b75f838519c536f75`, `#110825`, `#94462`, `#110825`, `#110825`, `#110005`, `#109998`, `#110005`, `#110018`, `#109996`, `#42611`, `#110057`, `#110087`, `#107762`, `#110044`, `#110679`, `#95147`, `#77111`, `#111102`, `#108940`, `#111042`, `#85396`, `#81116`, `#76236`, `#88338`, `#110825`, `#110005`, `#110018`, `#94462`, `#110005`, `#110018`, `#42611`, `#111042`, `#110057`, `#110087`, `#95147`, `#95193`, `#98105`, `#110981`, `#111102`, `#108940`, `#107762`, `#110044`, `#110679`
  - files: `hermes_cli/config_defaults.py`, `hermes_cli/config_env_defaults.py`, `plugins/platforms/discord/adapter.py`, `plugins/platforms/discord/live_transcription.py`, `plugins/platforms/discord/voice_receiver.py`, `tests/gateway/test_discord_voice_stale_binding.py`, `tests/plugins/platforms/test_discord_live_transcription.py`, `tests/plugins/platforms/test_discord_stt_modes.py`, `tests/tools/test_pre_transcription_hook.py`, `tests/tools/test_transcription_command_providers.py`, `tests/tools/test_transcription_plugin_dispatch.py`, `tests/tools/test_transcription_tools.py`, `tests/tools/test_transcription_tools_provider_override.py`, `tools/transcription_cloud.py`, `tools/transcription_command.py`, `tools/transcription_tools.py`, `website/docs/user-guide/features/voice-mode.md`

## Fix status

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