latest version sounds computer generated

souzatharsis / podcastfy

An Open Source alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

https://www.podcastfy.ai

Apache License 2.0

734 stars 82 forks source link

latest version sounds computer generated #122

Closed ralyodio closed 3 hours ago

ralyodio commented 4 hours ago

THe quality of the podcast audio has gone down, it sound very artificial.

word_count: 3000
conversation_style:
  - humorous
  - analytical
podcast_name: Byte Broadcast
podcast_tagline: "Byte Broadcast, your weekly gateway to the intersection of web development, artificial intelligence, and cryptocurrency, where complex concepts are decoded into byte-sized insights."
engagement_techniques:
  - cliffhangers
  - vivid imagery
  - audience prompts
creativity: 0.7

souzatharsis commented 4 hours ago

I've updated the default tts-model to be Microsoft's Edge ('edge'), so it's free and it does not require an API Key.

Feel free to try other models by setting tts-model to 'openai' or 'elevenlabs'. Both will require API Keys.

Please let me know if that helps.

ralyodio commented 4 hours ago

How do I switch to eleven labs? I have an api key.

souzatharsis commented 3 hours ago

CLI:

python -m podcastfy.client --url https://example.com/article1 --url https://example.com/article2 --tts-model elevenlabs

Package:

audio_file_multi = generate_podcast( urls=[urls], tts_model="elevenlabs")

On Sun, Oct 27, 2024 at 9:12 AM ralyodio @.***> wrote:

How do I switch to eleven labs? I have an api key.

— Reply to this email directly, view it on GitHub https://github.com/souzatharsis/podcastfy/issues/122#issuecomment-2439990156, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADTMY3NYLYBPGLWH55YADLDZ5TKDJAVCNFSM6AAAAABQVXMHUGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDIMZZHE4TAMJVGY . You are receiving this because you commented.Message ID: @.***>

ralyodio commented 3 hours ago

thanks