Open source Amazon Polly alternatives

Voice cutoff at the end of words — Polish language

“**VoxCPM version:** 2.0.2 --- ### Description When generating speech in **Polish**, the voice occasionally cuts off abruptly at the end of a word. The final syllable or consonant is truncated, making the output sound unnatural. This happens with default generation parameters.…”

RVC AI Voice on Daw(vst) Plugin

“Sunflower Industries is a VST (AU) plugin for RVC voice conversion for all!, simply load up Path&Index file of your choice and will convert audio file to near-zero letency.”

AMD Support - Segmentation Fault

“System: ``` Ubuntu 22.04 LTS Intel i5-12600k 32GB DDR4 AMD Radeon RX 6650 XT ``` Manually installed PyTorch 2.0.1 for rocm. Then installed requirements from requirements.txt. webui boots up without problems but when trying inference or training I get the following message: ```…”

OpenVoice: Versatile Instant Voice Cloning

“> This repository is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which prohibits commercial usage. MyShell reserves the ability to detect whether an audio is generated by OpenVoice, no matter whether the watermark is added or not.…”

OpenVoice: Instant Voice Cloning

“There's a difference from starting the project by using OpenVoice vs hiring an actor for 90% of the work but then cloning their voice because you can' be bothered to reschedule the same actor for creative changes. But if you start that project by making a voice sound like Morgan…”

Chatterbox TTS

“(Didn't carefully read your reply. What follows are the results of cat-ing a text file in the CLI. Will give the new textbox a whirl in the morning PDT. A truly heartfelt thanks for helping me work with Chatterbox TTS!) Absolutely blown away. I fed it the first page of Gibson's…”

Chatterbox TTS

“> Chatterbox is fantastic. > I created an API wrapper that also makes installation easier (Dockerized as well) Gave your wrapper a try and, wow, I'm blown away by both Chatterbox TTS and your API wrapper. Excuse the rudimentary level of what follows. Was looking for a quick and…”

Whistle: Speech to Text in 16.9 MB

“I find the quality of transcription quite poor with a high error rate. And I'm using an Devine podcast quality microphone. IMHO the error rate is comparable to Dragon Speech of twenty years ago. It seems to me the speech models don't take into account the context of the words in…”

Mozilla Common Voice Adds 16 New Languages and 4,600 New Hours of Speech

“This is silly. Common Voice is not adding NVidia-specific features; what would that even look like for a database? There is no comparison to be made between donating resources to an openly licensed database and encouraging developers to optimize their games for proprietary APIs.…”

Leon Sans, a geometric typeface made with code

“This is fascinating, there is quite a bit of overlap with a font that I started designing recently: I do small projects on CNC machines, and I got annoyed at having to trace both sides of a character, when using the outline of a standard font. In response, I created the…”

Leon Sans, a geometric typeface made with code

“Super cool work! Congrats for the birth of baby Leon :-) -- I got interested in typographic animation a while back, there are two related Wikipedia pages: "Motion Graphics" [1] and "Kinetic Typography" [2]. There is not a lot of info describing algorithms to perform Kinetic…”

Finetunining for better Results?

“So I assume, the collab isn't actually finetuning. This makes sense because for some voices I can get close enough for it sounds good. But like let's say my voice. I have no idea why but it keeps making me sound like a Posh British man. Any way to improve the cloning of…”

is there any way to make it read longer like 20-30mins?

“I can get 23 seconds out of it but you'd think that it would be possible. Also are the emotional stresses automatic?”

Doc translate

“Doc translate”

docker: Error response from daemon: Head " denied

“docker: Error response from daemon: Head " denied”

Show HN: Open-Source TypeScript Framework for AI Agents – VoltAgent

“Hi HN, I'm one of the founders of VoltAgent. Over the past months, we've been building it with a simple focus: AI development lacks real-time observability. When you work with agents, it's often a black box. You write some code, run it, and just hope it behaves. If something…”

Show HN: Open-Source TypeScript Framework for AI Agents – VoltAgent

“Voltagent’s UI is stunning. Do you have plans to add nocode action types. Sometimes it is easier to start with nocode and switch to coding when necessary.”

Demucs Music Source Separation

“This is an AI/ML system by Meta which can separate recorded music into four “stems” - drums, bass, vocals and other. It’s not the first one (Deezer open sourced Spleeter a few years back which is now widely used) but I think the results from Demucs are super impressive - it…”

How I use it?

“I tried to install for 5 hours but I never go more far than the first step. I always got this error: 'conda env update -f environment-cpu.yml EnvironmentFileNotFound: '/Users/montserratbartoky/environment-cpu.yml' file not found' A video tutorial is the perfect thing for help us…”

LINUX: Local Whisper transcription errror

“**Describe the bug** Record not been able to be transcripted. **To Reproduce** Steps to reproduce the behavior: 1. git pull 2. ELECTRON_DISABLE_SANDBOX=1 npm run dev 3. Download models 4. Start record with hot-key **Expected behavior** Copy in the clipboard of the transcription…”

It wont type to forms or streamlabs

“I tried using OpenWhisper to type on forms it wont type it will type on browser when typing a url and in warcraft but it wont on streamlabs chat bot or app or on forms or gemini”

An issue with the preprocessing part of LibriTTS.

“Hello!🤗 When I'm working with the LibriTTS dataset, I noticed that the generated test.json and train.json files do not include the corresponding text for each audio sample. This absence of text information causes an error when trying to extract the phonemes later on.…”

Limit realtime transcription time

“Currently if real time transcription continues for a long time then sentence appear to be a huge so it's processing takes a lot of time even with using Cuda. Is that possible to set something like maximum_audio_duration etc to process smaller chunks of text instead of it all?”

macOS

“Code： ```from RealtimeSTT import AudioToTextRecorder import ssl ssl._create_default_https_context = ssl._create_unverified_context import torch model, _ = torch.hub.load(repo_or_dir="snakers4/silero-vad", model="silero_vad", verbose=True) if __name__ == '__main__': recorder =…”