In Episode 2 of Creative Flux, Pierson Marks (@piersonmarks) and Bilal Tahir (@deepwhitman) explore recent text-to-speech advancements from model providers like ElevenLabs V3 and OpenAI. They highlight where generative voice is today, where it is going, and how the industry is adopting this new technology.

Chapters

00:00 Introduction to Creative Flux

03:05 Exploring Text-to-Speech Technology

06:08 The Evolution of Speech Recognition

08:45 Advancements in Text-to-Speech Models

11:52 Comparing Text-to-Speech Providers

15:09 Voice Agents vs. Creative Applications

17:52 The Future of Conversational AI

23:33 Exploring API Access and New Features

24:38 Innovations in Audio Inpainting

28:06 Gemini TTS and AI Studio Overview

30:53 The Role of AI Studio for Developers

34:22 The Future of Local Models and Open Source

39:25 The Need for Abstraction Layers in TTS

44:02 The Rapid Evolution of Media Generation

Links:
- Elevenlabs: https://elevenlabs.io/app/speech-synthesis/text-to-speech
- Elevenlabs v3 intro: https://elevenlabs.io/docs/models#eleven-v3-alpha
- Openai Fm: https://www.openai.fm/
- Playai inpaint & dialog: https://fal.ai/models/fal-ai/playai/inpaint/diffusion
- Kokoro: https://fal.ai/models/fal-ai/kokoro/american-english
- Google ai studio: https://aistudio.google.com/prompts/new_chat
- Google AI studio for TTS: https://aistudio.google.com/generate-speech
- Minimax hailuo -02: https://fal.ai/models/fal-ai/minimax/hailuo-02/standard/image-to-video
- Seedance lite: https://fal.ai/models/fal-ai/bytedance/seedance/v1/lite/text-to-video