bark
TTS
bark | TTS | |
---|---|---|
67 | 232 | |
32,784 | 29,631 | |
3.8% | 4.7% | |
5.4 | 9.4 | |
7 days ago | 1 day ago | |
Jupyter Notebook | Python | |
MIT License | Mozilla Public License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
bark
-
Exploring Bark, the Open Source Text-to-Speech Model
!pip install git+https://github.com/suno-ai/bark.git
-
AI-generated sad girl with piano performs the text of the MIT License
To my knowledge, the model being used for this is "chirp" which is 'based on' bark[1], an AI text to speech model.
The github page for bark links to a page about chirp, which returns a 404 page for me [2]. that the model for suno.ai's song generator isn't too much different than the text to speech model.
My hunch is that it was something like a coincidence that the bark model was capable of producing music, and that was spun off into this product. Unfortunately, there seems to still be issues with bark when generating long (like book length) spoken audio. Which is too bad, as someone who's worked jobs that require lots of driving, it would be awesome to be able to have any text read to me in a natural sounding voice.
[1]https://github.com/suno-ai/bark
-
Generating music in the waveform domain (2020)
Stable-audio and MusicGen sounds better than Jukebox.
But the best so far is Suno.ai ( https://app.suno.ai ) especially with their V3 model they have very impressive results, the fidelity is not studio quality but they're getting very close.
It's very likely based on their TTS model they have released before Bark, but trained on more data and with higher resolution.
https://github.com/suno-ai/bark
-
Stable-Audio-Demo
https://github.com/suno-ai/bark
> Bark was developed for research purposes. It is not a conventional text-to-speech model but instead a fully generative text-to-audio model, which can deviate in unexpected ways from provided prompts. Suno does not take responsibility for any output generated. Use at your own risk, and please act responsibly.
I've generated probably >200 songs now with Suno, of which perhaps 10 have been any good, and I can't detect any pattern in terms of the outputs.
Here's another one which is pretty good. I accidentally copied and pasted the prompt and lyrics, and it's amazing to me how 'musically' it renders the prompt:
-
Suno AI
hahah wow! cool :-)
PS: OT, I am reading this Bark thing(https://github.com/suno-ai/bark). Can I run it locally on a Macbook 2015 with 8GB RAM?
-
SDXL + SVD + Suno AI
I have it locally. The model is on huggingface. It runs with about 8GB VRAM.
- [discussion] text to voice generation for textbooks
-
Open Source Libraries
suno-ai/bark
- Weird A.I. Yankovic, a cursed deep dive into the world of voice cloning
- FLaNK Stack Weekly 2 October 2023
TTS
-
Ask HN: Open-source, local Text-to-Speech (TTS) generators
I just noticed that https://coqui.ai/ is "Shutting down".
I'm building a web app (React / Django) which takes a list of affirmations & goals (in Markdown files), puts them into a database (SQlite), and uses voice synthesis to create voice audio files of the phrases. These are combined with a relaxed backing track (ffmpeg), made into playlists of 10-20 phrases (randomly sampled, or according to a theme: "mind" "body" "soul") and then play automatically in the morning & evening (cron). This allows you to persistently hear & vocalize your own goals & good vibes over time.
I had been planning to use Coqui TTS as the local text-to-speech engine, but with this cancellation, I'd love to hear from the community what is a great open-source, local text-to-speech engine?
Generally, I learn both the highest quality commercially available technology (example: ElevenLabs), and also the best open-source equivalent. Would love to hear suggestions & perspectives on this. What voice synth tools are you investing your time into learning & building with?
-
OpenAI deems its voice cloning tool too risky for general release
lol this marketing technique is getting very old. https://github.com/coqui-ai/TTS is already amazing and open source.
-
What things are happening in ML that we can't hear oer the din of LLMs?
Not sure how relevant this is but note that Coqui TTS (the realistic TTS) has already shut down
https://coqui.ai
-
Base TTS (Amazon): The largest text-to-speech model to-date
I've used coqui.ai's TTS models[0] and library[1] to great success. I was able to get cloned voice to be rendered in about 80% of the audio clip length, and I believe you can also stream the response. Do note the model license for XTTS, it is one they wrote themselves that has some restrictions.
[0] https://huggingface.co/coqui/XTTS-v2
[1] https://github.com/coqui-ai/TTS
- FLaNK Stack Weekly 12 February 2024
- Coqui Is Shutting Down
-
Coqui.ai Is Shutting Down
My only exposure to Coqui was their text to speech software. If I remember correctly the website was a commercialized service with TTS and probably some other related things. I hope the software work continues in the open.
https://github.com/coqui-ai/TTS
-
Hello guys, any selfhosted alternative to eleven labs?
Coqui.ai TTS (https://github.com/coqui-ai/TTS)
-
Demo of Anagnorisis - completely local recommendation system powered by Llama 2. Radio mode. Work in progress.
"tts_models/multilingual/multi-dataset/xtts_v2" model from https://github.com/coqui-ai/TTS. It gives pretty good results and works with references, so it's pretty easy to change the voice. By the way the source code of the project is open: https://github.com/volotat/Anagnorisis but be ready, the code is pretty raw for now.
-
XTTS voice cloning with only a seconds of audio
A recent update to their GitHub also has a no-code gradio ui to facilitate fine-tuning and inferencing locally. https://github.com/coqui-ai/TTS/releases/tag/v0.21.3
What are some alternatives?
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
SadTalker - [CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
Retrieval-based-Voice-Conversion-WebUI - Easily train a good VC model with voice data <= 10 mins!
silero-models - Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
whisper.cpp - Port of OpenAI's Whisper model in C/C++
vosk-api - Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
audiolm-pytorch - Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
piper - A fast, local neural text to speech system