Global hotkey
Bind OSTT to a system-wide shortcut. Press to open the recorder, speak, press again to stop. Nova-3 transcribes and the result lands in your clipboard or stdout — without touching the mouse.
Deepgram Nova-3 from the command line.
OSTT gives you direct access to Deepgram Nova-3 from your terminal. Bind it to a global hotkey, pipe the transcript to your clipboard, a file, or an AI tool — on Linux and macOS.
Deepgram Nova-3
Fast, accurate, affordable transcription.
Nova-3 is Deepgram's flagship general-purpose speech model. It delivers low latency and high accuracy across a wide range of accents and audio conditions — at a fraction of the cost of comparable cloud models. OSTT connects it directly to your keyboard and shell.
# Set Nova-3 as your default in ~/.config/ostt/ostt.toml
[transcription]
provider = "deepgram"
model = "nova-3"
[deepgram.nova-3.params]
smart_format = true
diarize = true
# Or pick it interactively
ostt model
# Record with a hotkey, transcribe with Nova-3, copy to clipboard
ostt launch -cAny output target
Send Nova-3 transcription to the clipboard with -c, write to a file with -o, or print to stdout and pipe it wherever you like. One command, any destination.
File transcription
Transcribe existing audio files with ostt transcribe meeting.mp3. Run it in scripts, cron jobs, or CI pipelines. Nova-3 handles MP3, WAV, and most common formats.
Pipe to AI tools
Use -p to run a processing action after transcription. Route Nova-3 output directly into OpenCode, Claude Code, Gemini CLI, or any shell command without manual copy-paste.
Retry without re-recording
OSTT saves every recording locally. Run ostt retry to re-transcribe the same audio with Nova-3, or switch to any other provider — no need to speak again.
Switch providers freely
OSTT is provider-agnostic. Use Nova-3 as your default and override per-call when you need a different model or want to compare accuracy. One config file covers all providers.
Workflow
From speech to useful output.
1. RecordPress your global hotkey or run
ostt in the terminal.2. TranscribeNova-3 processes the audio via the Deepgram API.
3. ProcessOptionally run AI prompts or shell commands on the result.
4. SendPrint to stdout, copy to clipboard, write to a file, or pipe onward.
Pipeline
Nova-3 inside your shell.
OSTT is a standard Unix tool. Nova-3 transcription is just text on stdout — pipe it through jq, sed, or any CLI tool. Use the -p flag to chain processing actions without leaving the terminal.
# Transcribe and pipe to a custom script
ostt | my-script.sh
# Transcribe mp3, summarize with AI, write to file
ostt transcribe meeting.mp3 -p summary -o notes.md
# Record, run "clean" processing action, copy to clipboard
ostt -p clean -c