voice-transcribe
Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).
When & Why to Use This Skill
This Claude skill provides a high-performance audio transcription solution powered by OpenAI's gpt-4o-mini-transcribe model. It is specifically designed to handle various audio formats and improve transcription accuracy through customizable vocabulary hints and automated text replacements. By integrating with the 'uv' python tool, it offers a fast, cached, and developer-friendly way to convert voice memos and recordings into precise text, making it ideal for users who need to process audio content within their automated workflows.
Use Cases
- Quickly transcribing voice memos from messaging apps like WhatsApp to read and respond to content without listening to the audio.
- Converting recorded meetings, interviews, or lectures into searchable text documents for better documentation and knowledge retrieval.
- Improving transcription quality for niche industries by adding technical jargon, brand names, or specific terminology to the custom vocabulary list.
- Automating batch audio processing by piping transcription outputs into other CLI tools or text editors for further analysis.
- Correcting consistent AI transcription errors automatically using the text replacement feature for guaranteed accuracy.
| name | voice-transcribe |
|---|---|
| description | Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/). |
voice-transcribe
transcribe audio files using openai's gpt-4o-mini-transcribe model.
when to use
when receiving voice memos (especially via whatsapp), just run:
uv run /Users/darin/clawd/skills/voice-transcribe/transcribe <audio-file>
then respond based on the transcribed content.
fixing transcription errors
if darin says a word was transcribed wrong, add it to vocab.txt (for hints) or replacements.txt (for guaranteed fix). see sections below.
supported formats
- mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg, opus
examples
# transcribe a voice memo
transcribe /tmp/voice-memo.ogg
# pipe to other tools
transcribe /tmp/memo.ogg | pbcopy
setup
- add your openai api key to
/Users/darin/clawd/skills/voice-transcribe/.env:OPENAI_API_KEY=sk-...
custom vocabulary
add words to vocab.txt (one per line) to help the model recognize names/jargon:
Clawdis
Clawdbot
text replacements
if the model still gets something wrong, add a replacement to replacements.txt:
wrong spelling -> correct spelling
notes
- assumes english (no language detection)
- uses gpt-4o-mini-transcribe model specifically
- caches by sha256 of audio file