Overview of Text to Speech Approaches

This week we will take a look at Speech to Text models in three different categories:

1. Products that create audio from text in an offline mode
2. APIs that can be integrated into a product
3. Open source models that you can host

Each of these presents different challenges that we’ll cover such as latency, realism, and hallucination. Here’s the list of products and models so far, so if you don’t see your favorite in the list, let me know and we’ll check it out as well:

• Parler
• Coqui
• Bark
• OpenAI (6 models)
• BASE TTS (Amazon)
• MetaVoice
• MeloTTS
• ElevenLabs
• Facebook MMS

Also – a few of us went to the Huntsville AI and Machine Learning Technology Exchange and Expo last week, so we might do an overview of those topics if time permits.

Links & Other Events:

• 2024 AI Symposium Recorded Sessions – https://www.youtube.com/playlist?list=PLvvHQqQynqmtkQuLsvfFtmy0OohBcA5H4
• 2025 AI Symposium – https://www.rocketcenter.com/institute
• Hugging Face Text to Speech – https://huggingface.co/tasks/text-to-speech 

Details:

• Date – 11/20/2024
• Time – 6-7:30pm
• Zoom –https://us02web.zoom.us/j/89971705398?pwd=CndWhnWX6sbtgQLaAbn8CctPjzcxjV.1

As always, I really appreciate the support and replies to these emails. You can also help by following, sharing, liking, and dropping comments on my posts on LinkedIn and Facebook – especially the ones directly for the Huntsville AI page on LinkedIn – https://www.linkedin.com/company/huntsville-ai