Zg/add openai (#18)

Zg/improve logging (#8)

Add opengraph image asset and route to serve image from project for social media previews

Add custom error message for Hume APInrate limit error

Update generic error message

Simplify integration logic in app.py

Clean up integration code

raise friendlier error message to UI from integration code

Update hume integration to use Hume python sdk

reduce Hume requests timeout limit

Update anthropic and elevenlabs integrations to retry with exponential backoff.

added emotional text examples to character prompt for arena

Relax timeout configs for Hume TTS calls, add exponential backoff, add logs for logging call times

Adjust normalized Claude prompt for text input

Improve voice descriptions and normalized claude prompt

Update API integration code to be async

Update Anthropic integration to be async

Update database layer and application logic for db interaction to be async

Clean up comments for prompts

New character descriptions

Add '_' prefix to private methods throughout project, cleans up formatting and comments/docstrings

Fix types in integrations package

more explicit control flow

Add database for persisting votes, and functions to write to db, update submit_voting_results function to write results to DB

Move env var validation util to config, refactor to fix linting errors across project

Remove unused imports

Simplify UI logic in app.py, add logic for handling empty character description inputs.

Update file clean up logic to delete audio files older than 30 minuteds when writing new audio file to static/audio directory.

Move business logic out of app.py, refactor code to call hume once specifying 2 generations instead of call Hume twice

Improve Hume errors, fix error message text in UI

Improve Anthropic error handling, add UnretryableAnthropicError

improve 11labs error handling

Update application flow to accept a character description and normalize a prompt for claude

Refactor tts integration functions to write audio to file and return file path, audio players to play mp3 file written to temp folder, fix audioplayer loading, remove unused imports

Update eleven labs integration to consume the voice generation api

Update Hume integration to use OCTAVE TTS endpoint, update Elevenlabs integration to use voice design endpoint, no longer specify voice since voices are now generated

Update system prompt for claude and placeholder sample prompts

Finalize pre-commit configuration

Add formatter (black) and format all code in src directory— using black default formatting configuration

Improve ElevenLabs integration documentation

Restore encapsulation for ElevenLabs integration, update TTS functions to return the voice name in addition to the audio

Update UI to compare Hume vs Elevenlabs 50% of the time, and Hume vs Hume 50% of the time

Update documentation and fix typos across project

Clean up doc strings

Remove dark theme styles

Update claude system prompt, sample prompts, and max prompt input limit

Clean up docstrings across files

Improve Hume API error handling

Improve ElevenLabs API error handling

Improve Anthropic API error handling