README.md

podscript

podscript is a tool to generate transcripts for podcasts (and other similar audio files), using LLMs and Speech-to-Text (STT) APIs.

Install

> go install github.com/deepakjois/podscript@latest

> ~/go/bin/podscript --help

Web UI

Podscript has a web based UI for convenience

> podscript web
Starting server on port 8080

This runs a web server on at http://localhost:8080

For more advanced usage, see the CLI section below.

CLI Getting started

# Configure keys for supported services (OpenAI, Anthropic, Deepgram etc)
# and write them to $HOME/.podscript.toml
podscript configure

# Transcribe a YouTube Video by formatting and cleaning up autogenerated captions
podscript ytt https://www.youtube.com/watch?v=aO1-6X_f74M

# Transcribe audio from a URL using deepgram speech-to-text API
#
# Deepgram and AssemblyAI subcommands support `--from-url` for
# passing audio URLs, and `--from-file` to pass audio files.
podscript deepgram --from-url  https://audio.listennotes.com/e/p/d6cc86364eb540c1a30a1cac2b77b82c/

# Transcribe audio from a file using Groq's whisper model
#  Groq only supports audio files.
podscript groq --file huberman.mp3

More Info

Models for ytt subcommand

The ytt subommand uses the gpt-4o model by default. Use --model flag to set a different model. The following are supported:

• gpt-4o
• gpt-4o-mini
• claude-3-5-sonnet-20241022
• claude-3-5-haiku-20241022
• llama-3.3-70b-versatile
• llama-3.1-8b-instant

Transcript from audio URLs and files

Tip

You can find the audio download link for a podcast on ListenNotes under the More menu

podscript supports the following Speech-To-Text (STT) APIs:

• Deepgram (which as of Jan 2025 provides $200 free signup credit!)
• Assembly AI (which as of Oct 2024 is free to use within your credit limits and they provide $50 credits free on signup).
• Groq (which as of Jul 2024 is in beta and free to use within your rate limits).

Feedback

Feel free to drop me a note on X or Email Me

License

MIT