_josh_meyer_

hi there o/

i'm josh, the first author. been cooking this up for a while and happy to answer questions / comments!

the github repo: https://github.com/anthropics/ClaudeForFoundationModels

an optimistic rebuttal to Amdahl's law: https://lawsofsoftwareengineering.com/laws/gustafsons-law/

the original 1967 paper: https://dl.acm.org/doi/epdf/10.1145/1465482.1465560

local news video: https://www.youtube.com/watch?v=tz84xF6tn-M

a 5-minute video version (with local TTS model) https://tldr-api.manatee.work/v/dmYg0U

icymi, here's the claude skill: https://github.com/veris-ai/veris-skills

Author here: Looking forward to discussion!

nw_wrld is an event-driven sequencer for triggering visuals using web technologies. It enables users to scale up audiovisual compositions for prototyping, demos, exhibitions, and live performances. Users code their own visual modules, then orchestrate them using the project's native UI composer.

OP here -- I work at Veris and built this. Happy to answer questions about the methodology!

SantaBench, a fun benchmark with a serious methodology. The task: play a cheeky Santa agent who researches users online and roasts them based on their social media.

also, not everyone has access. I used (afaik) the only "academic paper --> narrated video" converter, and it just went into beta a couple weeks ago

Wasn't meant to imply the opposite. The video even has a watermark clearly saying it's generated. I genuinely found the video useful, so decided to share.

excellent post -- I turned it into a video :) https://supabase.manatee.work/storage/v1/object/public/video...

complete overview of the Model Context Protocol

Code and a recipe for XTTS_v1.1 GPT encoder training is released under the Mozilla Public License 2.0

XTTS model release (Text-to-Speech and voice cloning)

# From the release notes:

This model is trained on top of XTTS v1, using output masking. We mask the part of the output that is used as the audio prompt while training and don't compute loss for that segment. This helps us to resolve the hallucination issue that V1 experienced.

- Add Japanese - Resolve the hallucination issue (repeating the audio prompt) - Increased expressivity - Added ne_hifigan that was trained without denoising that brought some EQ and compression profile that might be unwanted for some use-cases

XTTS + Whisper + Mistral 7B

Coqui releases model weights for XTTS generative Voice model. Demo live on Huggingface

an example pipeline for midjourney / runwayML / coqui to create a video

Oh this is cool:)

hi there! what kind of better API support do you mean?

Prompt-to-voice creates a new, unique voice given a text prompt. Similar to stable diffusion, but for voices. Then those voices can generate speech via TTS.

Newest release from https://coqui.ai

Direct-able, controllable generative AI Voices

Voice cloning from a segment of Merkel via Coqui.ai

Map of interesting companies and applications in the Generative AI Landscape, according to Sequoia (Oct. 2022)

Waitlist for early access to the Coqui Studio

imo this kind of tech is useful to supplement the artist, not replace them. You listen to a singer because you know their voice more than anything. Bob Dylan was a pretty bad singer, but I listen to him because of some emotional connection.

From the Coqui TTS project <https://github.com/coqui-ai/TTS>