TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Bark – Text-prompted generative audio model

416 pointsby obi1kenobiabout 2 years ago

28 comments

gkucskoabout 2 years ago
Hey, one of the Suno founders&#x2F;creators of Bark here. Thanks for all the comments, we love seeing how we can improve things in the future. At Suno we work on audio foundation models, creating speech, music, sounds effects etc….<p>Text to speech was a natural playground for us to share with the community and get some feedback. Given that this model is a full GPT model, the text input is merely a guidance and the model can technically create any audio from scratch even without input text, aka hallucinations or audio continuation.<p>When used as a TTS model, it’s very different from the awesome high quality TTS models already available. It produces a wider range of audio – that could be a high quality studio recording of an actor or the same text leading to two people shouting in an argument at a noisy bar. Excited to see what the community can build and what we can learn for future products.<p>Please let us know with any feedback, or if you’re interested in working on this: bark@suno.ai
评论 #35646730 未加载
评论 #35646502 未加载
评论 #35645236 未加载
评论 #35647892 未加载
评论 #35646323 未加载
calnyabout 2 years ago
Very cool. Side note: bark-gpt.com is already taken for a dog translator: &quot;The world’s first AI powered, real-time communications tool between humans and their furry best friends.&quot;[0] I only know this because my law firm partner&#x27;s name is Bark, and I wanted to automate some legal work and name the software &quot;Bark GPT&quot; after him.<p>[0] <a href="https:&#x2F;&#x2F;www.bark-gpt.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.bark-gpt.com&#x2F;</a>
评论 #35646339 未加载
评论 #35644063 未加载
评论 #35645828 未加载
评论 #35645268 未加载
ripperdocabout 2 years ago
Am I hallucinating or didn&#x27;t several of the examples have background audio artifacts, like it&#x27;s been trained on speech with noisy backgrounds, I&#x27;m guessing audio from movies paired with subtitles? Having random background audio can make it quite hard to use in production.
评论 #35647569 未加载
评论 #35645456 未加载
newswasboringabout 2 years ago
Man I know this is HN, and I know we have a certain decorum we should be maintaining, but with the recent activity in this field the most appropriate response to these posts is &quot;4bit when?&quot; or &quot;f16 when?&quot;. Not sure which one is applicable. I am having no luck running it on a 6GB vram gpu, so I guess its the 16 bit floating point one.
评论 #35646784 未加载
评论 #35646954 未加载
tasty_freezeabout 2 years ago
A few years a back someone had the genius idea of making a robo-answering phone program that would give vague but encouraging replies when it received some unsolicited sales pitch. Although it was a fixed sequence of responses, it fooled some callers for a surprisingly long time.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=XSoOrlh5i1k">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=XSoOrlh5i1k</a><p>Someone needs to hook create the plumbing to capture speech to text, feed it to a GPT script that has been told how to reply to such call center calls, then send that back through a TTS generator like this one.<p>To overcome any latency issues, it could build in a ploy to buy time like the old script did, eg, make the robo-answerer sound like a somewhat addled old man who has to think before each reply, perhaps prefixing responses with &quot;hmm, ahh, ...&quot; to buy time to generate the response.
jdprgmabout 2 years ago
It seems like a lot of the entries in TTS are either close sourced saas apps or something like this with limitations on customizing it. It seems clearly inevitable and likely only months away that a high quality unrestricted open source option for things like voice cloning will emerge so i&#x27;m not sure why these projects are even really bothering trying to stop it. I think in order for TTS to have its StableDiffusion moment it will just be a matter of an unrestricted easily trainable open source model.
评论 #35645784 未加载
generalizationsabout 2 years ago
Is there likely to be a way to stream this audio in the future? As in, here&#x27;s an incoming stream of text, generate the audio on-the-fly instead of all at once.
vlugorillaabout 2 years ago
Great news! It&#x27;s astounding how quickly technology is advancing. Only yesterday, I was wondering about when a new model for text-to-speech would be developed, and today a game-changing model has been released! This new model is simply incredible!
评论 #35646073 未加载
rckabout 2 years ago
Any idea what the training data for this is? Looking at the model, it looks like it is literally just copy-paste from Karpathy&#x27;s nanoGPT, so the training data is what&#x27;s most interesting. Pretty amazing anyway.
评论 #35644453 未加载
DarthNeboabout 2 years ago
Imagine Torvalds saying the same in the context of linux- &#x27;to mitigate misuse of this technology, we limit the audio history prompts to a limited set of Suno-provided...&#x27;
bdgabout 2 years ago
Ok, the German example caught me -- it&#x27;s too real. &quot;But maybe it would be faster if...&quot;
评论 #35646610 未加载
miki123211about 2 years ago
The fact that this is open source and can generate more thann just speech is really nice, but for speech itself, it&#x27;s much lower quality than what Eleven Labs provides.<p>All the open source models I&#x27;ve seen so far have this weird kind of neural fuzziness to them. I don&#x27;t know what Eleven does better, but there&#x27;s definitely a big difference.
评论 #35646080 未加载
评论 #35646579 未加载
quaintdevabout 2 years ago
Good naming choice after OpenAIs whisper for speech to text. Bark is fitting name for text to speech.
sschuellerabout 2 years ago
&quot;However, to mitigate misuse of this technology, we limit the audio history prompts to a limited set of Suno-provided, fully synthetic options to choose from for each language.&quot;<p>Isn&#x27;t this open source and can be easily removed or am I missing something?
评论 #35646246 未加载
causiabout 2 years ago
Some of it is very impressive although some of it seems about equal to the TTS built into my phone. How long until someone can package this up and make a program that takes in epubs and spits out mp3s?
billconanabout 2 years ago
I tried it. It seems to hallucinate easily. The generated audio isn&#x27;t what I provided.<p>It seems to be easily reproducible if I specify a non-existing speaker?<p>audio_array = generate_audio(text_prompt, &#x27;en_speaker_3&#x27;)
nathiasabout 2 years ago
I hope you reconsider the misuse mitigation, I&#x27;m trying to clone my voice, but so far the other tools weren&#x27;t that great ...
评论 #35646147 未加载
itomatoabout 2 years ago
“Last nights Phish performance is proof that God loves us.” But in Portuguese.<p><a href="https:&#x2F;&#x2F;suno-ai.notion.site&#x2F;Bark-Examples-5edae8b02a604b54a42244ba45ebc2e2" rel="nofollow">https:&#x2F;&#x2F;suno-ai.notion.site&#x2F;Bark-Examples-5edae8b02a604b54a4...</a>
xingpedabout 2 years ago
Does it sound fairly robotic&#x2F;static-y to anyone else or just me? Doesn&#x27;t sound any better than any other TTS software I&#x27;ve tried and in fact sounds a bit worse, like it&#x27;s noisy.
101008about 2 years ago
The Spanish example (Miguel) is really bad.
评论 #35644205 未加载
评论 #35644131 未加载
seydorabout 2 years ago
Well i can see it becoming sexy soon
评论 #35644041 未加载
treerunnerabout 2 years ago
Can someone briefly explain how a model for a specific language is made for this tool?
computerexabout 2 years ago
How do I save the audio array to a file on the file system?
评论 #35663902 未加载
awaller1about 2 years ago
this is incredible
pfa344about 2 years ago
Hello how are you doing
txtaiabout 2 years ago
Excellent work! Hope to see a version that has a friendlier commercial license in the future (current version is CC-BY 4.0 NC).
mysteryboxabout 2 years ago
WTH1!!!
wgreenberg24about 2 years ago
Awesome stuff! Can’t wait to see where this company goes