These are the same samples on https://erogol.github.io/ddc-samples/

All models are trained using Coqui-TTS https://github.com/coqui-ai/TTS

long_sentence1

hard_sentencec3

hard_sentencec2

hard_sentencec1

Composed and Produced by Raymond Hayter, May 2021.

Video here: https://youtu.be/gaWsh0oFZuw

Lyrics:

I am super user
I am super user
I am super user
I am super.

Music. Electronic.
Melody. Harmonic.
Play Loud. Strategic.
Isolate. From Public.

Movement. Bionic.
Speaking. Laconic.
Soda. Is Tonic.
Allergies. Are chronic.

Humour. Tragic.
Socially. Robotic.
Friendship. Platonic.
Rejection. Ironic.
  
Study. Work Ethic.
Focus. And Logic.
Game Plan. Strategic.
Success. Economic.

---
Synthesizers & Percussion:
Chipspeech
System 8
JP-08
D-05
Sirin
Diva
Albino
Synclavier V
Synthi V
VK-2
Algoritm
Parsec
Repro-1
Microtonic

Super User - by Cosmic Address

haha shadow singing mario go do the mario

Shadow Sings Do The Mario (Uberduck.ai)

ESSAY using ClosersCopy's AI writing assistant.

Amazon's Neural Voice: Matthew
Topic: Expository Essay about Artificial Intelligence
Checkout ClosersCopy Here: https://swiy.io/ClosersCopyLifetime

Expository Essay About Artificial Intelligence

Travis Willingham

Sarvente

Fantastic Cuts

High performance Deep Learning models for Text2Speech tasks.
Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech).
Speaker Encoder to compute speaker embeddings efficiently.
Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN)
Fast and efficient model training.
Detailed training logs on console and Tensorboard.
Support for multi-speaker TTS.
Efficient Multi-GPUs training.
Ability to convert PyTorch models to Tensorflow 2.0 and TFLite for inference.
Released models in PyTorch, Tensorflow and TFLite.
Tools to curate Text2Speech datasets underdataset_analysis.
Demo server for model testing.
Notebooks for extensive model benchmarking.
Modular (but not too much) code base enabling easy testing for new ideas.

TTS - demo

Developer of Friendship - A Sonic 2 Creepypasta and Hedgehog's Bloody Collection.

Will mostly post audio memes/edits, or siivagunner-styled rips.

CD Rips and other Junk

Audio Commentaries hopefully coming soon

I'm obsessed with synthesizers and music of the 80s!. Here is music from my solo project Cosmic Address, and collaboration projects Pacific Deep (with Carl Grace), isunray (Jay Hay), and a few other collaborations.  

Synths & Drums: Roland JX-8P, System-8, JP-08, D-05, TR-8 (with 7x7 expansion), Moog Sirin, Korg Arp Odyssey

DAW: Cockos Reaper, ReasonStudios Reason
Primary Virtual Instruments:  u-he Repro 1 & 5, Diva, Korg Legacy Polysix, M1, Wavestation, Mono/Poly, Synapse The Legend, Obsession, Antidote, Dune, TAL Uno LX, Arturia Collection.

#80s #retro #synthpop #synthwave #synth

https://github.com/coqui-ai/TTS
www.coqui.ai

New tracks tagged #text-to-speech