gateway: format voice transcript as π γ...γ - #1
Merged
Conversation
maiixu
force-pushed
the
claude/voice-transcript-format
branch
from
April 11, 2026 23:16
e69b6cd to
fb1d523
Compare
Reads ~/.hermes/stt_hotwords.txt and passes terms as initial_prompt (faster-whisper) or prompt (Groq/OpenAI API). File read fresh each call.
maiixu
force-pushed
the
claude/voice-transcript-format
branch
from
April 11, 2026 23:23
fb1d523 to
b638203
Compare
Store transcript in self._pending_voice_transcript during enrichment. Before returning the response to the user, prepend π γtranscriptγ. LLM still receives the original [The user sent a voice message~] format. No LLM tokens spent on formatting β done at gateway layer.
maiixu
force-pushed
the
claude/voice-transcript-format
branch
from
April 11, 2026 23:33
b638203 to
b13d767
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Two patches on top of upstream:
1.
stt: inject hotwords as initial_prompt(already committed)Reads
~/.hermes/stt_hotwords.txtand passes terms asinitial_prompt/prompton every transcription call across all three providers (local faster-whisper, Groq, OpenAI). File is read fresh each call β no gateway restart needed.2.
gateway: format voice transcript as π γ...γ(this PR)Changes the voice message format injected into the LLM context from:
to:
Cleaner display in Telegram, saves ~10 context tokens per voice message, and removes the need for SOUL.md to reformat it.
Why
Both changes are personal patches to upstream
NousResearch/hermes-agent. This fork exists to carry these patches while staying synced with upstream.