Audio

You can record audio as you record with OBS Studio.

Or with audacity and bring it later.

sudo snap install audacity
#sudo snap remove audacity

In between your notes, you can also do it with LogSeq.

But what to do / how to process audio?

With those, I created:

Speech Rater Creation

st audio and OpenAI | Post

Speech Raiter

Streamlit Speech rater - Source Code on Github

I have been building TTS/S2T Web Apps:

FastAPI Speech Rater

Using OpenAI with fastAPI for audio

TTS

You can do local TTS as I was doing here

I was initially using transcription here to create the audio for my tech yt videos.

That was based on OpenAI keys, see how

You can also use Kokoro:

pip install kokoro-onnx soundfile --user

• https://github.com/resemble-ai/chatterbox

MIT | SoTA open-source TTS

S2T / Transcription

You can try locally with Whisper:

pip install openai-whisper --user

See also the OpenAI way

Other OSS Audio Apps

• https://github.com/beyondcode/writeout.ai

MIT |Transcribe and translate your audio files - for free