Hacker News with Generative AI: Text-to-Speech

Generate audiobooks from E-books with Kokoro-82M (claudio.uk)
Kokoro v0.19 is a recently published text-to-speech model with just 82M params and very high-quality output.

Text-to-Speech, Generative AI, Software, Audiobooks

415 points by csantini 3 days ago | 242 comments

MathReader: Text-to-Speech for Mathematical Documents [pdf] (arxiv.org)
TTS (Text-to-Speech) document reader from Microsoft, Adobe, Apple, and OpenAI have been serviced worldwide. They provide relatively good TTS results for general plain text, but sometimes skip contents or provide unsatisfactory results for mathematical expressions.

Text-to-Speech, Mathematical Documents, Accessibility, AI, Research

18 points by bikenaga 3 days ago | 0 comments

Show HN: New Cartesia Text-to-Speech Model (cartesia.ai)
Real-time multimodal intelligence for every device

Text-to-Speech, AI, Show HN, Software, Cartesia

10 points by cartesia 37 days ago | 0 comments

Play Dialog: A contextual turn-taking TTS model like NotebookLM Playground (play.ai)
PlayNoteAgentsPlaygroundPricingAPICommunityConversation (2 Speakers)Narration (1 Speaker)LanguageSpeaker 1 VoiceSpeaker 2 VoiceConnecting...Random PromptCreate Voice Clone

Speech Recognition, Artificial Intelligence, Text-to-Speech, Machine Learning

49 points by dulldata 65 days ago | 13 comments

A CC-By Open-Source TTS Model with Voice Cloning (huggingface.co)
OuteTTS-0.1-350M is a novel text-to-speech synthesis model that leverages pure language modeling without external adapters or complex architectures, built upon the LLaMa architecture using our Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis is achievable through a straightforward approach using crafted prompts and audio tokens.

Open Source, Text-to-Speech, Voice Cloning, AI, Language Modeling

131 points by amrrs 74 days ago | 31 comments

Show HN: I made a tutorial of how to use free edge TTS API with deno.js [video] (youtube.com)

Tutorials, Programming, Text-to-Speech, Deno.js, JavaScript

5 points by neochau 77 days ago | 0 comments

Play 3.0 mini – A lightweight, reliable, cost-efficient Multilingual TTS model (play.ht)
Today we’re releasing our most capable and conversational voice model that can speak in 30+ languages using any voice or accent, with industry leading speed and accuracy. We’re also releasing 50+ new conversational AI voices across languages.

Multilingual, Artificial Intelligence, Text-to-Speech, Software

258 points by amrrs 95 days ago | 83 comments

Free Text-to-Speech App with natural voices (elevenlabs.io)

Text-to-Speech, Artificial Intelligence, Software, Accessibility

38 points by jslakro 148 days ago | 29 comments

Show HN: Using AI to generate custom sounds from text (image-effects.com)

Generative AI, Artificial Intelligence, Sound Design, Text-to-Speech

19 points by Mabroorahmed 169 days ago | 8 comments

Show HN: I generated 70k audiobooks with OpenAI Text-to-Speech (listenly.io)

OpenAI, Text-to-Speech, Audiobooks, Generative AI, Show HN

140 points by evan_ry 188 days ago | 109 comments

Coqui.ai TTS: A Deep Learning Toolkit for Text-to-Speech (github.com/coqui-ai)