add opensouce version

replace gemini with gpt 4o-mini

allow the gemini api key to be passed via gradio

replace html string constants with actual files

chore: Remove unnecessary environment variables in Dockerfile

chore: add comment

serve via granian and add standard head tags and static files

allow for concurrency on generating transcripts

update the prompt to make it less likely to include brackets with variables and to have the main points of the text reiterated at the end of the dialogue

chore: Refactor PDF file reading in generate_audio function

feat: Add note about audio compatibility with Safari

feat: Add Sentry error tracking for improved error handling

Refactor PDF file reading in generate_audio function

fetch audio in parallel

Refactor PDF file reading in generate_audio function

feat: Fix PDF file reading in generate_audio function

feat: Update Gradio interface configuration with description and transcript output

feat: Add multiple voice options for podcast narration

Refactor README.md to remove "Converter" from the project name

add link to github

add examples

feat: Add description to Gradio interface configuration

add transcript to output

chore: Update dependencies and add tenacity library for retrying validation errors

chore: Remove unnecessary logger.info call in generate_audio function

feat: Update DialogueItem voice property to use speaker instead of deprecated values

chore: Update virtual environment setup in README.md

chore: Remove unnecessary fields from Gradio interface configuration

chore: Update Gradio interface configuration and remove unnecessary fields

chore: Update Gradio interface configuration and remove unnecessary fields

chore: Update Dockerfile and docker-compose.yml for Gradio server configuration

chore: Update Dockerfile and docker-compose.yml for Gradio server port configuration

dockerize

pdf's now work

text works

we're getting audio

initial commit