[HN Gopher] Sopro TTS: A 169M model with zero-shot voice cloning...
       ___________________________________________________________________
        
       Sopro TTS: A 169M model with zero-shot voice cloning that runs on
       the CPU
        
       Author : sammyyyyyyy
       Score  : 342 points
       Date   : 2026-01-08 20:37 UTC (1 days ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | lukebechtel wrote:
       | Very cool. I'd love a slightly larger version with hopefully
       | improved voice quality.
       | 
       | Nice work!
        
         | sammyyyyyyy wrote:
         | Thanks! Yeah I kinda postponed publishing it until it was a bit
         | better, but as a perfectionist, it would have never been
         | published
        
           | lukebechtel wrote:
           | understood! Glad you shipped.
        
       | convivialdingo wrote:
       | Impressive! The cloning and voice affect is great. Has a slight
       | warble in the voice on long vowels, but not a huge issue. I'll
       | definitely check it out - we could use voice generation for
       | alerting on one of our projects (no GPUs on hardware).
        
         | sammyyyyyyy wrote:
         | Cool! Yeah the voice quality really depends on the reference
         | audio. Also mess with the parameters. All the feedback is
         | welcome
        
       | realityfactchex wrote:
       | That's cool and useful.
       | 
       | IMO, the best alternative is Chatterbox-TTS-Server [0] (slower,
       | but quite high quality).
       | 
       | [0] https://github.com/devnen/Chatterbox-TTS-Server
        
         | iLoveOncall wrote:
         | Chatterbox-TTS has a MUCH MUCH better output quality though,
         | the quality of the output from Sopro TTS (based on the video
         | embedded on GitHub) is absolutely terrible and completely
         | unusable for any serious application, while Chatterbox has
         | incredible outputs.
         | 
         | I have an RTX5090, so not exactly what most consumers will have
         | but still accessible, and it's also very fast, around 2 seconds
         | of audio per 1 second of generation.
         | 
         | Here's an example I just generated (first try, 22 seconds
         | runtime, 14 seconds of generation):
         | https://jumpshare.com/s/Vl92l7Rm0IhiIk0jGors
         | 
         | Here's another one, 20 seconds of generation, 30 seconds of
         | runtime, which clones a voice from a Youtuber (I don't use it
         | for nefarious reasons, it's just for the demo):
         | https://jumpshare.com/s/Y61duHpqvkmNfKr4hGFs with the original
         | source for the voice: https://www.youtube.com/@ArbitorIan
        
           | sammyyyyyyy wrote:
           | You should try it! I wouldn't say it's the best, far from
           | that. But also wouldn't say it's terrible. If you have a
           | 5090, then yes, you can run much more powerful models in real
           | time. Chatterbox is a great model though
        
             | iLoveOncall wrote:
             | > But also wouldn't say it's terrible.
             | 
             | But you included 3 samples on your GitHub video and they
             | all sound extremely robotic and have very bad artifacts?
        
           | kkzz99 wrote:
           | I've been using Higgs-Audio for a while now as the primary
           | TTS system. How would you say does Chatterbox compare to it
           | if you have experience?
        
             | iLoveOncall wrote:
             | I haven't used it. I compared it with T5Gemma TTS that came
             | out recently and Chatterbox is much better in all aspects,
             | but especially in voice cloning where T5Gemma basically did
             | not work.
        
         | BoxOfRain wrote:
         | I quite like IndexTTS2 personally, it does voice cloning and
         | also lets you modulate emotion manually through emotion vectors
         | which I've found quite a powerful tool. It's not necessarily
         | something everyone needs, but it's really cool technology in my
         | opinion.
         | 
         | It's been particularly useful for a model orchestration project
         | I've been working on. I have an external emotion classification
         | model driving both the LLM's persona and the TTS output so it
         | stays relatively consistent. The affect system also influences
         | which memories are retrieved; it's more likely to retrieve
         | 'memories' created in the current affect state. IndexTTS2 was
         | pretty much the only TTS that gives the level of control I felt
         | was necessary.
        
           | realityfactchex wrote:
           | Wow, the IndexTTS2 demo is very good. Definitely going to
           | check that out. Thanks.
           | 
           | [0] https://indextts2.org
        
       | blitzar wrote:
       | Mission impossible cloning skills without the long compile time.
       | 
       | "The pleasure of Buzby's company is what I most enjoy. He put a
       | tack on Miss Yancy's chair ..."
       | 
       | https://www.youtube.com/watch?v=H2kIN9PgvNo
       | 
       | https://literalminded.wordpress.com/2006/05/05/a-panphonic-p...
        
       | btbuildem wrote:
       | It's impressive given the constraints!
       | 
       | Would you consider releasing a more capable version that renders
       | with fewer artifacts (and maybe requires a bit more processing
       | power)?
       | 
       | Chatterbox is my go-to, this could be a nice alternative were it
       | capable of high-fidelity results!
        
         | sammyyyyyyy wrote:
         | This is my side "hobby". And compute is quite expensive. But if
         | the community's responsive is good, I will definitely think
         | about it! Btw, chatterbox is a great model and inspiration
        
           | bicepjai wrote:
           | Thanks can you share details about compute economics you
           | dealt with ?
        
             | sammyyyyyyy wrote:
             | Yeah sure. The training was about ~250 dollars, which is
             | quite low by today's standards. And I spent a bit more on
             | ablations and research
        
           | littlestymaar wrote:
           | Very cool work, especially for a hobby project.
           | 
           | Do you have any plans to publish a blog post on _how_ you did
           | that? ?What training data and how much? Your training and
           | ablations methodology, etc.
        
       | elaus wrote:
       | Very nice to have done this by yourself, locally.
       | 
       | I wish there was an open/local tts model with voice cloning as
       | good as 11l (for non-english languages even)
        
         | sammyyyyyyy wrote:
         | Yeah, we are not quite there, but I'm sure we are not far
         | either
        
       | SoftTalker wrote:
       | What does "zero-shot" mean in this context?
        
         | nateb2022 wrote:
         | > Zero-shot learning (ZSL) is a problem setup in deep learning
         | where, at test time, a learner observes samples from classes
         | which were not observed during training, and needs to predict
         | the class that they belong to. The name is a play on words
         | based on the earlier concept of one-shot learning, in which
         | classification can be learned from only one, or a few,
         | examples.
         | 
         | https://en.wikipedia.org/wiki/Zero-shot_learning
         | 
         | edit: since there seems to be some degree of confusion
         | regarding this definition, I'll break it down more simply:
         | 
         | We are modeling the conditional probability P(Audio|Voice). If
         | the model samples from this distribution for a Voice class not
         | observed during training, it is by definition zero-shot.
         | 
         | "Prediction" here is not a simple classification, but the
         | estimation of this conditional probability distribution for a
         | Voice class not observed during training.
         | 
         | Providing reference audio to a model at inference-time is no
         | different than including an AGENTS.md when interacting with an
         | LLM. You're providing context, not updating the model weights.
        
           | woodson wrote:
           | This generic answer from Wikipedia is not very helpful in
           | this context. Zero-shot voice cloning in TTS usually means
           | that data of the target speaker you want the generated speech
           | to sound like does not need to be included in the training
           | data used to train the TTS models. In other words, you can
           | provide an audio sample of the target speaker together with
           | the text to be spoken to generate the audio that sounds like
           | it was spoken by that speaker.
        
             | coder543 wrote:
             | Why wouldn't that be one-shot voice cloning? The concept of
             | calling it zero shot doesn't really make sense to me.
        
               | geocar wrote:
               | So if you get your target to record (say) 1 hour of
               | audio, that's a one-shot.
               | 
               | If you didn't do that (because you have 100 hours of
               | other people talking), that's zero-shots, no?
        
               | nateb2022 wrote:
               | > So if you get your target to record (say) 1 hour of
               | audio, that's a one-shot.
               | 
               | No, that would still be zero shot. Providing inference-
               | time context (in this case, audio) is no different than
               | giving a prompt to an LLM. Think of it as analogous to an
               | AGENTS.md included in a prompt. You're not retraining the
               | model, you're simply putting the rest of the prompt into
               | context.
               | 
               | If you actually stopped and fine-tuned the model weights
               | on that single clip, that would be one-shot learning.
        
               | ImPostingOnHN wrote:
               | _> Providing inference-time context (in this case, audio)
               | is no different than giving a prompt to an LLM._
               | 
               | Right... And you have 0-shot prompts ( _" give me a list
               | of animals"_), 1-shot prompts ( _" give me a list of
               | animals, for example: a cat"_), 2-shot prompts ( _" give
               | me a list of animals, for example: a cat; a dog"_), etc.
               | 
               | The "shot" refers to how many examples are provided to
               | the LLM _in the prompt_ , and have nothing to do with
               | training or tuning, in every context I've ever seen.
        
               | nateb2022 wrote:
               | > Right... And you have 0-shot prompts ("give me a list
               | of animals"), 1-shot prompts ("give me a list of animals,
               | for example: a cat"), 2-shot prompts ("give me a list of
               | animals, for example: a cat; a dog"), etc.
               | 
               | > The "shot" refers to how many examples are provided to
               | the LLM in the prompt, and have nothing to do with
               | training or tuning, in every context I've ever seen.
               | 
               | In formal ML, "shot" refers to the number of samples
               | available for a specific class during the training phase.
               | You're describing a colloquial usage of the term found
               | only in prompt engineering.
               | 
               | You can't apply an LLMism to a voice cloning model where
               | standard ML definitions apply.
        
               | woodson wrote:
               | I don't disagree, but that's what people started calling
               | it. Zero-shot doesn't make sense anyway, as how would the
               | model know what voice it should sound like (unless it's a
               | celebrity voice or similar included in the training data
               | where it's enough to specify a name).
        
               | nateb2022 wrote:
               | > Zero-shot doesn't make sense anyway, as how would the
               | model know what voice it should sound like (unless it's a
               | celebrity voice or similar included in the training data
               | where it's enough to specify a name).
               | 
               | It makes perfect sense; you are simply confusing training
               | samples with inference context. "Zero-shot" refers to
               | zero gradient updates (retraining) required to handle a
               | new class. It does not mean "zero input information."
               | 
               | > how would the model know what voice it should sound
               | like
               | 
               | It uses the reference audio just like a text based model
               | uses a prompt.
               | 
               | > unless it's a celebrity voice or similar included in
               | the training data where it's enough to specify a name
               | 
               | If the voice is in the training data, that is literally
               | the opposite of zero-shot. The entire point of zero-shot
               | is that the model has never encountered the speaker
               | before.
        
               | magicalhippo wrote:
               | With LLMs I've seen zero-shot used to describe scenarios
               | where there's no example, it "take this and output JSON",
               | while one-shot has the prompt include an example like
               | "take this and output JSON, for this data the JSON should
               | look like this".
               | 
               | Thus if you feed a the model target voice, ie an example
               | of the desired output vouce, it sure seems like it should
               | be classified as one-shot.
               | 
               | However it seems the zero-shot in voice cloning is
               | relative to learning, and in contrast to one-shot
               | learning[1].
               | 
               | So a bit overloaded term causing confusion from what I
               | can gather.
               | 
               | [1]: https://en.wikipedia.org/wiki/One-
               | shot_learning_(computer_vi...
        
               | nateb2022 wrote:
               | The confusion clears up if you stop conflating contextual
               | conditioning (prompting) with actual Learning (weight
               | updates). For LLMs, "few-shot prompting" is technically a
               | misnomer that stuck; you are just establishing a pattern
               | in the context window, not training the model.
               | 
               | In voice cloning, the reference audio is simply the
               | input, not a training example. You wouldn't say an image
               | classifier is doing "one-shot learning" just because you
               | fed it one image to classify. That image is the input.
               | Similarly, the reference audio is the input that
               | conditions the generation. It is zero-shot because the
               | model's weights were never optimized for that specific
               | speaker's manifold.
        
               | ben_w wrote:
               | Zero-shot means zero-retraining, so think along the lines
               | of "Do you need to modify the weights? Or can you keep
               | the weights fixed and you only need to supply an
               | example?"
               | 
               | As with other replies, yes this is a silly name.
        
               | nateb2022 wrote:
               | > Zero-shot means zero-retraining, so think along the
               | lines of "Do you need to modify the weights? Or can you
               | keep the weights fixed and you only need to supply an
               | example?"
               | 
               | I would caution that using the term "example" suggests
               | further learning happens at inference-time, which isn't
               | the case.
               | 
               | For LLMs, the entire prompt is the input and conveys both
               | the style and the content vectors. In zero-shot voice
               | cloning, we provide the exact same inputs vectors but
               | just decoupled. Providing reference audio is no different
               | than including "Answer in the style of Sir Isaac Newton"
               | in an LLM's prompt. The model doesn't 'learn' the voice;
               | it simply applies the style vector to the content during
               | the forward pass.
        
               | nateb2022 wrote:
               | Providing inference-time context (in this case, audio) is
               | no different than giving a prompt to an LLM. Think of it
               | as analogous to an AGENTS.md included in a prompt. You're
               | not retraining the model, you're simply putting the rest
               | of the prompt into context.
               | 
               | If you actually stopped and fine-tuned the model weights
               | on that single clip, that would be one-shot learning.
        
               | coder543 wrote:
               | To me, a closer analogy is In Context Learning.
               | 
               | In the olden days of 2023, you didn't just find instruct-
               | tuned models sitting on every shelf.
               | 
               | You could use a base model that has only undergone
               | pretraining and can only generate text continuations
               | based on the input it receives. If you provided the model
               | with several examples of a question followed by an
               | answer, and then provided a new question followed by a
               | blank for the next answer, the model understood from the
               | context that it needed to answer the question. This is
               | the most primitive use of ICL, and a very basic way to
               | achieve limited instruction following behavior.
               | 
               | With this few-shot example, I would call that few-shot
               | ICL. Not zero shot, even though the model weights are
               | locked.
               | 
               | But, I am learning that it is technically called zero
               | shot, and I will accept this, even if I think it is a
               | confusingly named concept.
        
               | oofbey wrote:
               | It's nonsensical to call it "zero shot" when a sample of
               | the voice is provided. The term "zero shot cloning"
               | implies you have some representation of the voice from
               | another domain - e.g. a text description of the voice.
               | What they're doing is ABSOLUTELY one shot cloning. I
               | don't care if lots of STT folks use the term this way,
               | they're wrong.
        
             | nateb2022 wrote:
             | > This generic answer from Wikipedia is not very helpful in
             | this context.
             | 
             | Actually, the general definition fits this context
             | perfectly. In machine learning terms, a specific 'speaker'
             | is simply a 'class.' Therefore, a model generating audio
             | for a speaker it never saw during training is the exact
             | definition of the Zero-Shot Learning problem setup: "a
             | learner observes samples from classes which were not
             | observed during training," as I quoted.
             | 
             | Your explanation just rephrases the very definition you
             | dismissed.
        
               | woodson wrote:
               | From your definition:
               | 
               | > a learner observes samples from classes which were not
               | observed during training, and needs to predict the class
               | that they belong to.
               | 
               | That's not what happens in zero-shot voice cloning, which
               | is why I dismissed your definition copied from Wikipedia.
        
               | nateb2022 wrote:
               | > That's not what happens in zero-shot voice cloning
               | 
               | It is exactly what happens. You are confusing the task
               | (classification vs. generation) with the learning
               | paradigm (zero-shot).
               | 
               | In the voice cloning context, the class is the speaker's
               | voice (not observed during training), samples of which
               | are generated by the machine learning model.
               | 
               | The definition applies 1:1. During inference, it is
               | predicting the conditional probability distribution of
               | audio samples that belong to that unseen class. It is
               | "predict[ing] the class that they belong to," which very
               | same class was "not observed during training."
               | 
               | You're getting hung up on the semantics.
        
               | woodson wrote:
               | Jeez, OP asked what it means in this context (zero-shot
               | voice cloning), where you quoted a generic definition
               | copied from Wikipedia. I defined it concretely for this
               | context. Don't take it as a slight, there is no need to
               | get all argumentative.
        
           | numpad0 wrote:
           | I think the point is it's not zero shot if a sample is
           | needed. A system that require one sample is usually
           | considered one-shot, or few-shot if it needs few, etc etc.
        
         | throwaway132448 wrote:
         | The *-shot jargon is just in-crowd nonsense that has been
         | meaningless since day one (or zero). Like Big O notation but
         | even more arbitrary (as evidenced by all the answers to your
         | comment).
        
       | derefr wrote:
       | Is there yet any model like this, but which works as a "speech
       | plus speech to speech" voice modulator -- i.e. taking a fixed
       | audio sample (the prompt), plus a continuous audio stream (the
       | input), and transforming any speech component of the input to
       | have the tone and timbre of the voice in the prompt, resulting in
       | a continuous audio output stream? (Ideally, while passing through
       | non-speech parts of the input audio stream; but those could also
       | be handled other ways, with traditional source separation
       | techniques, microphone arrays, etc.)
       | 
       | Though I suppose, for the use-case I'm thinking of (v-tubers),
       | you don't really need the ability to dynamically change the
       | prompt; so you could also simplify this to a continuous single-
       | stream "speech to speech" model, which gets its target vocal
       | timbre burned into it during an expensive (but one-time) fine-
       | tuning step.
        
         | vunderba wrote:
         | I don't know about open models, but ElevenLabs has had this
         | idea of mapping intonation/emotion/inflections onto a
         | designated TTS voice for a while.
         | 
         | https://elevenlabs.io/blog/speech-to-speech
        
         | gcr wrote:
         | Chatterbox TTS does this in "voice cloning" mode but you have
         | to implement the streaming part yourself.
         | 
         | There are two inputs: audio A ("style") and B ("content"). The
         | timbre is taken from A, and the content, pronunciation,
         | prosody, accent, etc is taken from B.
         | 
         | Strictly soeaking, voice cloning models like this and
         | chatterbox are not "TTS" - they're better thought of as
         | "S+STS", that is, speech+style to speech
        
         | qingcharles wrote:
         | There must be something out there that does this reliably as I
         | often see/hear v-tubers doing it.
        
         | lumerios wrote:
         | yes, check out RVC (retrieval voice conversation) which I
         | believe is the only good open source voice changer. Currently
         | there's a bit of a conflict between the original creator and
         | current developers. So don't use the main fork. I think you'll
         | be able to find a more up-to-date fork that's in english.
        
       | nunobrito wrote:
       | Muito fixe. Now the next challenge (for me) is how to convert
       | this to DART and run on Android. :-)
        
         | sammyyyyyyy wrote:
         | Obrigado! Quando (e se fizeres isso) manda pm!
        
       | woodson wrote:
       | Does the 169M include the ~90M params for the Mimi codec?
       | Interesting approach using FiLM for speaker conditioning.
        
         | sammyyyyyyy wrote:
         | No, it doesn't.
        
       | brikym wrote:
       | A scammers dream.
        
         | jacquesm wrote:
         | That's exactly how I see it.
        
           | soulofmischief wrote:
           | Unfortunately, we have to prepare for a future where this
           | kind of stuff is everywhere. We will have to rethink how
           | trust is modeled online and offline.
        
         | gosub100 wrote:
         | unfortunately I think you're right, the cons massively outweigh
         | the pros.
         | 
         | One constructive use would be making on-demand audiobooks.
        
         | CoastalCoder wrote:
         | I agree.
         | 
         | I'd be curious to hear why its advocates believe that this is a
         | net win for society.
        
           | Alex2037 wrote:
           | it doesn't need to be. are video games a net win for society?
           | is porn?
        
       | jacquesm wrote:
       | What could possibly go wrong...
       | 
       | Don't you ever think about what the balance of good and bad is
       | when you make something like this? What's the upside? What's the
       | downside?
       | 
       | In this particular case I can only see downsides, if there are
       | upsides I'd love to hear about them. All I see is my elderly
       | family members getting 'me' on their phones asking for help, and
       | falling for it.
       | 
       | I've gotten into the habit of waiting for the other person to
       | speak first when I answer the phone now and the number is unknown
       | to me.
        
         | sammyyyyyyy wrote:
         | Yes, you are right. However, there are many upsides to this
         | kind of technology. For example, it can restore the voices of
         | people who were affected by numerous diseases
        
           | jacquesm wrote:
           | Ok, that's an interesting angle, I had not thought of that,
           | but of course you'd still need a good sample of them from
           | before that happened. Thank you for the explanation.
        
         | Alex2037 wrote:
         | are you under the impression that this is the first such tool?
         | it's not. it's not even the hundredth. this Pandora's box has
         | been opened a long time ago.
        
         | idiotsecant wrote:
         | There is no such thing as bad technology.
        
           | jacquesm wrote:
           | That is simply not true. There is lots of bad technology.
        
             | idiotsecant wrote:
             | Like what? There's no technology that simply by existing
             | causes harm to the world, people do that part.
        
               | cookiengineer wrote:
               | > Like what? There's no technology that simply by
               | existing causes harm to the world, people do that part.
               | 
               | People create that technology, therefore enforcing their
               | own lack of morals and lack of ethics onto it. That's the
               | part that most humans in the post-digital age seem to
               | ignore to purposefully deflect and absolve themselves
               | from any responsibilities.
               | 
               | Also, companies will always be controlled by humans that
               | optimized their life for greed, not by the ones that
               | specialized on philosophical implications.
               | 
               | The inventors of novichok or the nuclear bomb didn't have
               | "world peace" in mind. They had "world peace through me
               | enforcing my own will onto my enemies" in mind.
        
               | CamperBob2 wrote:
               | _The inventors of novichok or the nuclear bomb didn 't
               | have "world peace" in mind. They had "world peace through
               | me enforcing my own will onto my enemies" in mind._
               | 
               | I don't know about Novichok, but nuclear bombs have
               | stopped world wars, at least so far.
        
               | numpad0 wrote:
               | like that chemical weapon that was specifically designed
               | to react with gas mask absorbent materials so to activate
               | at the protected side so to circumvent filteration(long
               | banned since the end of WWI).
        
             | Alex2037 wrote:
             | who gets to decide which technology must be banned? the
             | same people who decide which books must be burned?
        
               | jacquesm wrote:
               | Surely that would be you.
        
           | CoastalCoder wrote:
           | > There is no such thing as bad technology.
           | 
           | If nothing else, it's a debate where we'd need to define our
           | terms.
        
           | burnt-resistor wrote:
           | I hate to admit it, but it's true. Technology is amoral and
           | neutral rather than morally directed, it can directed towards
           | profits, control, and nefarious goals, sure. It's the added
           | externalities in the form of lost jobs and suffering borne by
           | many and power gained by a few that technological advancement
           | enables. The decision to or how to use technology by human
           | decisions is where a moral crossroad exists and is considered
           | or ignored by the stakeholders involved. Substantive
           | engineering ethics isn't much of a thing anymore as long the
           | TC is enough, but performative complaints about napkins not
           | being 100% recycled or insufficient planted trees are the
           | ostensible substitutes.
        
         | jbaber wrote:
         | I am unhappy about the criminal dimension of voice cloning,
         | too, but there are plenty of use cases.
         | 
         | e.g. If I could have a (local!) clone of my own voice, I could
         | get lots of wait-on-the-phone chores done by typing on my
         | desktop to VOIP while accomplishing other things.
        
           | anigbrowl wrote:
           | But why do you need it to be a clone of _your_ voice? A
           | generic TTS like Siri or a vocaloid would be sufficient.
        
       | sergiotapia wrote:
       | It sounds a lot like RFK Jr! Does anyone have any more casual
       | examples?
        
       | guerrilla wrote:
       | I don't understand the comments here at all. I played the audio
       | and it sounds absolutely horrible, far worse than computer voices
       | sounded fifteen years ago. Not even the most feeble minded person
       | would mistake that as a human. Am I not hearing the same thing
       | everyone else is hearing? It sounds straight up corrupted to me.
       | Tested in different browsers, no difference.
        
         | sammyyyyyyy wrote:
         | As I said, some reference voices can lead to bad voice quality.
         | But if it sounds that bad, it's probably not it. Would love to
         | dig into it if you want
        
           | guerrilla wrote:
           | I mean I'm talking about the mp4. How could people possibly
           | be worried about scammers after listening to that?
        
             | sammyyyyyyy wrote:
             | I didn't specially cherry pick those examples. You can try
             | it anyway for yourself. But thanks for the feedback anyway
        
               | guerrilla wrote:
               | No shade on you. It's definitely impressive. I just
               | didn't understand people's reactions.
        
             | jrmg wrote:
             | It sounds like someone using an electrolarynx to me.
        
           | codefreakxff wrote:
           | I agree with the comment above. I have not logged into hacker
           | news in _years_ but did so today just to weigh in here. If
           | people are saying that the audio sounds great, then there is
           | definitely something going on with a subset of users where we
           | are only hearing garbled words with a LOT of distortion. This
           | does not sound like natural speech to met at all. It sounds
           | more like a warped cassette tape. And I do not mean to slight
           | your work at all. I am actually incredibly puzzled here to
           | understand why my perception of this is so radically
           | different from others!
        
             | guerrilla wrote:
             | Thank you for commenting. I wonder if this could be another
             | situation like "the dress" (2015) or maybe something is
             | wrong with our codecs...
        
               | Mashimo wrote:
               | No, nothing wrong with your codecs. It's sounds shitty.
               | But given the small size and speed it's still impressive.
               | 
               | It's like saying .kkrieger looks like a bad game, which
               | it does, but then again .kkrieger is only 96kb or
               | whatever.
        
               | guerrilla wrote:
               | How big are TTS models like this usually?
               | 
               | .kkrieger looks like an amazing game for the mid-90s.
               | It's incomprehensible that it's only 96kb.
        
               | Mashimo wrote:
               | Here is an overview:
               | https://www.inferless.com/learn/comparing-different-text-
               | to-...
               | 
               | Also keep in mind the processing time. The ^ article
               | above used a NVIDIA L4 with 24-GB VRAM. Sopro claims 7.5
               | second processing time on CPU for 30 seconds of audio!
               | 
               | If you want to get real good quality TTS, you should
               | check out elevenlabs.io
               | 
               | Different tools for different goals.
        
         | foolserrandboy wrote:
         | I thought it was RFK
        
           | serf wrote:
           | spasmodic dysphonia as a service.
        
         | jackyysq wrote:
         | same here, tried few different voices including my kids and my
         | own, the generated audio is not similar at all, it's not even a
         | proper voice
        
         | wildmXranat wrote:
         | Yes, if this selected piece is the best that was available to
         | be used as a showcase, it's immediately off putting in
         | distortion and mangling of pronunciation.
        
         | eigenvalue wrote:
         | Thank you, I was scrolling and scrolling in utter disbelief. It
         | sounds absolutely dreadful. Would drive me nuts to listen to
         | for more than a minute.
        
       | Gathering6678 wrote:
       | Emm...I played the sample audio and it was...horrible?
       | 
       | How is it voice cloning if even the sample doesn't sound like any
       | human being...
        
         | sammyyyyyyy wrote:
         | I should have posted the reference audio used with the
         | examples. Honestly it doesn't sound so different from them.
         | Voice cloning can be from a cartoon too, doesn't have to be
         | from a human being
        
           | nemomarx wrote:
           | A before / after with the reference and output seems useful
           | to me, and maybe a range from more generic to more
           | recognizable / celebrity voice samples so people can kinda
           | see how it tackles different ones?
           | 
           | (Prominent politician or actor or somebody with a distinct
           | speaking tone?)
        
           | Gathering6678 wrote:
           | That is probably a good idea. I was so confused listening to
           | the example.
        
         | sammyyyyyyy wrote:
         | Also, I didn't want to use known voices as the example, so I
         | ended up using generic ones from the datasets
        
       | krunck wrote:
       | I just had some amusing results using text with lots of
       | exclamations and turning up the temperature. Good fun.
        
       | yamal4321 wrote:
       | Tried english. There are similarities. Really impressive for such
       | budget Also increadibly easy to use, thanks for this
        
         | xiconfjs wrote:
         | But its english-only - so what else could you have tried?
         | Asking because I'm interested in a german version :)
        
       | VerifiedReports wrote:
       | What is "zero-shot" supposed to mean?
        
         | carteazy wrote:
         | I believe in this case it means that you do not need to provide
         | other voice samples to get a good clone.
        
           | spwa4 wrote:
           | It means there is _zero_ training involved in getting from
           | voice sample to voice duplicate. There used to be models that
           | take a voice sample, run 5 or 10 training iterations (which
           | of course takes 10 mins, or a few hours if you have hardware
           | as shitty as mine), and only then duplicate the voice.
           | 
           | This you give the voice sample as part of the input, and
           | immediately it tries to duplicate the voice.
        
             | x3haloed wrote:
             | Doesn't NeuTTS work the same way?
        
         | onion2k wrote:
         | zero-shot is a single prompt (maybe with additional context in
         | the form of files.)
         | 
         | few-shot is providing a few examples to steer the LLM
         | 
         | multi-shot is a longer cycle of prompts and refinement
        
           | moffkalast wrote:
           | if you had one-shot
           | 
           | or one opportunity
        
             | nake89 wrote:
             | to seize everything you ever wanted in one moment
        
               | raccer wrote:
               | Would you capture it or just let it slip? Yo
        
           | mikkupikku wrote:
           | I've been calling good results from a single prompt "single-
           | shot." Is this not right?
        
             | flimflamm wrote:
             | No as you could have multiple examples of expected output
             | in single prompt. You should just "ask" - that's zero shot.
             | If you "ask + provide" examples then you are in the n+1
             | shot realm. But I suppose terminology is shifting from
             | this...
        
           | samtheprogram wrote:
           | This is one-shot.
        
       | LoveMortuus wrote:
       | This is very cool! And it'll only get better. I do wonder, if, at
       | least as a patch-up job, they could do some light audio
       | processing to remove the raspiness from the voices.
        
       | armcat wrote:
       | Super nice! I've been using Kokoro locally, which is 82M
       | parameters and runs (and sounds) amazing!
       | https://huggingface.co/hexgrad/Kokoro-82M
        
         | machiaweliczny wrote:
         | I tried Kokoro-JS that I think runs in browser and it was too
         | way too slow with latency also not supporting language I wanted
        
           | armcat wrote:
           | I have a 5070 in my rig. What I'm running is Kokoro in a
           | Python/FastAPI backend - I also use local quantized models (I
           | swap between ministral-3 and Qwen3) as "the brains" (offload
           | to GPT-5.2 inc. web search for "complex" tasks or those
           | requiring the web). In the backend I use Kokoro and generate
           | wav bytes that I send to the frontend. The frontend is just a
           | simple HTML page with a textbox and a button, invoking a
           | `fetch()`. I type, and it responds back in audio. The round-
           | trip time is <1 second for me, unless it needs to call OpenAI
           | API for "complex" tasks. I am yet to integrate STT as well
           | and then the cycle is complete. That's the stack, and not
           | slow at all, but it depends on your HW.
        
         | machiaweliczny wrote:
         | BTW does anyone know of good assistant voice stack that's Open
         | Source? I used https://github.com/ricky0123/vad for voice
         | activation -> works good, then just using Web Speech API as
         | that's the fastest and then commercial TTS for speed as
         | couldn't find good one.
        
       | jokethrowaway wrote:
       | Sorry but the quality is too bad.
       | 
       | I'm sure it has its uses, but for anything practical I think Vibe
       | Voice is the only real OSS cloning option. F2/E5 are also very
       | good but has plenty of bad runs, you need to keep re-rolling.
        
       | jokethrowaway wrote:
       | I'm sure it has its uses, but for anything with a higher
       | requirement for quality, I think Vibe Voice is the only real OSS
       | cloning option.
       | 
       | F2/E5 are also very good but have plenty of bad runs, you need to
       | keep re-rolling until you get good outputs.
        
       | bcrl wrote:
       | What measures are being taken to ensure that this model isn't
       | used to lower the cost of fraudsters committing grandparent scams
       | by mimicking the voices of grandchildren?
        
         | burnt-resistor wrote:
         | None, obviously, and it's barking up the wrong tree. The genie
         | is already out of the bottle as there are zillions of similar
         | free services and software that do the same thing, and there's
         | no quick-fix panacea technological solutions to social and
         | legal problems. Legislation in every locality need to create
         | extremely harsh penalties for impersonating other people, and
         | elders need to be educated to ask questions of their family
         | members that only the real people would know the answers to.
        
       ___________________________________________________________________
       (page generated 2026-01-09 23:01 UTC)