HN Explorer

Ask HN: What's the current best local/open speech-to-speech setup?

265 points by dsrtslnd23 ↗ HN
I’m trying to do the “voice assistant” thing fully locally: mic → model → speaker, low latency, ideally streaming + interruptible (barge-in).

Qwen3 Omni looks perfect on paper (“real-time”, speech-to-speech, etc). But I’ve been poking around and I can’t find a single reproducible “here’s how I got the open weights doing real speech-to-speech locally” writeup. Lots of “speech in → text out” or “audio out after the model finishes”, but not a usable realtime voice loop. Feels like either (a) the tooling isn’t there yet, or (b) I’m missing the secret sauce.

What are people actually using in 2026 if they want open + local voice?

Is anyone doing true end-to-end speech models locally (streaming audio out), or is the SOTA still “streaming ASR + LLM + streaming TTS” glued together?

If you did get Qwen3 Omni speech-to-speech working: what stack (transformers / vLLM-omni / something else), what hardware, and is it actually realtime?

What’s the most “works today” combo on a single GPU?

Bonus: rough numbers people see for mic → first audio back

Would love pointers to repos, configs, or “this is the one that finally worked for me” war stories.

41 comments

[ 4.6 ms ] story [ 62.8 ms ] thread
jauntywundrkind
It was a little annoying getting old qt5 tools installed but I really enjoyed using dsnote / Speech Note. Huge model selection for my amd gpu. Good tool. I haven't done enough specific studying yet to give you suggestions for which model to go with. WhisperFlow is very popular.

Kyutai some very interesting work always. Their delayed streams work is bleeding edge & sounds very promising especially for low latency. Not sure why I have not yet tried it tbh. https://github.com/kyutai-labs/delayed-streams-modeling

There's also a really nice elegant simple app Handy. Only supports Whisper and Parakeet V3 but nice app & those are amazing models. https://github.com/cjpais/Handy

Johnny_Bonk
Anyone using any reasonably good small speech to text os models?
woudsma
I’m using whisper with superwhisper on my mac. I’ve assigned a key on my keyboard, when I press the key it starts listening and when I release it, the text gets copied to the current cursor location. It works pretty well.
d4rkp4ttern
Parakeet V3 is near-instant transcription, and the slight accuracy drop relative to the slower/bigger Whisper models is immaterial when talking to AIs that can “read between the lines”.
dfajgljsldkjag
It requires a bit of tinkering, but I think pipecat is the way to go. You can plug in pretty much any STT/LLM/TTS you want and go. It definitely supports local models but its up to you to get your hands on those models.

Not sure if there's any turnkey setups that are preconfigured for local install where you can just press play and go though.

Last I heard E2E speech to speech models are still pretty weak. I've had pretty bad results from gpt-realtime and that's a proprietary model, I'm assuming open source is a bit behind.

dsrtslnd23
yes, I am currently playing with pipecat - both with ASR + LLM + TTS pipeline and also speech to text (ultravox) + TTS but haven't been successful with local speech to speech setups yet.
storystarling
I suspect the glued pipeline is going to remain dominant for a while, mostly because the intermediate text layer is structural, not just a byproduct. If you drop the text for a pure E2E model, you suddenly lose the ability to easily inject RAG context or handle complex tool use. I've been building some agent workflows recently and having that text state to pass into something like LangGraph is the only way to reliably control the logic. Without it, you are basically flying blind on the backend.
DANmode
https://handy.computer got good marks from a very nontechnical user in my life this week!

Local, FOSS

benatkin
To save a click, it's just a fancy front end for Whisper plus a weaker CPU-only model. It has a demo video that seems impressive, but the speech is careful to sound casual while having no meaningful flaws that would cause it to mess up. If you want to make a speech to speech tool, which is what this post asks about, it would make more sense to go straight to Whisper.
marsbars241
Tangential: What hardware are you using for the interface on these? Is there a good array microphone that performs on par with echos/ghomes/homepods?
varik77
I have used https://github.com/SaynaAI/sayna . What I like the most is that you can switch between the providers easily and see what works for you the best. It also supports local models.
ripped_britches
speech to speech is not nearly as good as livekit IMO ("old school" sequence of transcribe, LLM, synthesize). depends on what you're doing of course, but this is just because the LLMs are just way smarter than the speech to speech models which are pretty much the worst (again IMO) at anything beyond basic banter. and livekit is just a framework so you can hook it up with any models in the stack. im not an expert on the local parts but i would assume this pretty easy to glue together.
soulofmischief
I have a great local assistant that works end-to-end with voice. It's built on local, web-first technologies, it fits small LLMs in memory and manages inference and TTS/STT without stuttering. I've been shaping it up over a couple years and constantly switching out new models.

If you want something simple that runs in browser, look at vosk-browser[0] and vits-web[1].

I'd also recommend checking out KittenTTS[2], I use it and it's great for the size/performance. However, you'd need to implement a custom JavaScript harness for the model since it's a python project. If you need help with that, shoot me an email and I can share some code.

There are other great approaches too if you don't mind python, personally I chose the web as a platform in order to make my agent fully portable and remote once I release it.

And of course, NVIDIA's new model just came out last week[3] but I haven't gotten to test it out just yet, and also there was the recent Sparrow-1[4] announcement which shows people are finally putting money into the problems plaguing voice agents that are rigged up from several models and glue infrastructure, vs a single end-to-end model or at least a conversational turn-taking model to keep things on rails.

[0] https://www.npmjs.com/package/vosk-browser

[1] https://github.com/diffusionstudio/vits-web

[2] https://github.com/KittenML/KittenTTS

[3] https://research.nvidia.com/labs/adlr/personaplex/

[4] https://www.tavus.io/post/sparrow-1-human-level-conversation...

doonielk
I did a MLX "streaming ASR + LLM + streaming TTS" pipeline in early 2024. I haven't worked on it since then so it's dated. There are now better versions of all the models I used.

I was able to conversational latency with the ability to interrupt the pipeline on a Mac, using a variety of tricks. It's MLX, so only relevant if you have a Mac.

https://github.com/andrewgph/local_voice

For MLX speech to speech, I've seen:

The mlx-audio package has some MLX implementations of speech to speech models: https://github.com/Blaizzy/mlx-audio/tree/main

kyutai Moshi, maybe old now but has a MLX implementation of their speech to speech model: https://github.com/kyutai-labs/moshi

zahlman
What exactly do you want the pipeline to do that cares about the input being "speech", or indeed that's different from just sending mic -> speaker directly? (I can imagine a few different things, but I want to figure out if your use case sounds like mine, or what suggestions are appropriate for what tasks.)
sails
Looking for an iOS app to test this as I’m generally curious about the capabilities of on devices TTS (yet to find an app, but there are loads for text gen)

It can’t be too far off considering Siri and TTS has been on devices for ages

andhuman
I built this recently. I used nvidia parakeet as STT, open wake word as the wake word detection, mistral ministral 14b as LLM and pocket tts for tts. Fits snugly in my 16 gb VRAM. Pocket is small and fast and has good enough voice cloning. I first used the chatterbox turbo model, which perform better and even supported some simple paralinguistic word like (chuckle) that made it more fun, but it was just a bit too big for my rig.
vulkoingim
I'm using https://spokenly.app/ in local mode, which is free. Very happy with it. It supports a bunch of models, including whisper and parakeet. Right now I'm mostly using parakeet v3 on my desktop, but it tends to do a bit more errors, although it is very fast. I cycle betwen it and Distil-Whisper Large V3.5, which is a bit slower.

On iOS I'm also using the same app, with the Apple Speech model, which I found out to be better performing for me than the parakeet/whisper. One drawback for the apple model is that you need iOS/Mac 26+ - and I haven't bothered to update to Tahoe on my mac.

Both of the models work instantly for me (Mac M1, iphone 17 Pro).

Edit: Aaaand I just saw that you're looking for speech-to-speech. Oops, still sleeping.

schobi
Oh... Having a local-only voice assistant would be great. Maybe someone can share the practical side of this.

Do you have the GPU running all day at 200W to scan for wake words? Or is that running on the machine you are working on anyway?

Is this running from a headset microphone (while sitting at the desk?) or more like a USB speakerphone? Is there an Alexa jailbreak / alternative firmware as a frontend and run this on a GPU hidden away?

timwis
Home Assistant have a fully local voice assistant experience that's very pluggable and customisable. I believe it uses a fast whisper model for STT and piper for TTS.

You can run it on a raspberry pi (or ideally an N100+), and for the microphone/speaker part, you can make your own or buy their off the shelf voice hardware, which works really well.

https://www.home-assistant.io/voice-pe/

sgt
While on this subject, what's the go to transcribe speech to text model (open source or proprietary, doesn't matter) if you have to support a lot of languages really well?
nsbk
I'm putting together a streaming ASR + LLM + streaming TTS setup based on Nvidia speech models: nemotron ASR and magpie TTS, pipecat to glue everything together, plus an LLM of your choice. I added Spanish support using canary models, as magpie models are English-only and it still works really well.

The work is based on a repo by pipecat that I forked and modified to be more comfortable to run (docker compose for the server and client), added Spanish support via canary models, and added Nvidia Ampere support so it can run on my 3090.

The use case is a conversation partner for my gf who is learning Spanish, and it works incredibly well. For LLM I settled with Mistral-Small-3.2-24B-Instruct-2506-Q4_K_S.gguf

https://github.com/nsbk/nemotron-january-2026

nsbk
I got the models all the way around. Nemotron-speech ASR is the one that is English-only. Magpie TTS is multilingual and can do both English and Spanish
d4rkp4ttern
This is not strictly speech-to-speech, but I quite like it when working with Claude Code or other CLI Agents:

STT: Handy [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative to bigger models is immaterial when you're talking to an AI. I always ask it to restate back to me what it understood, and it gives back a nicely structured version -- this helps confirm understanding as well as likely helps the CLI agent stay on track.

TTS: Pocket-TTS [2], just 100M params, and amazing speech quality (English only). I made a voice plugin [3] based on this, for Claude Code so it can speak out short updates whenever CC stops. It uses a non-blocking stop hook that calls a headless agent to create the 1/2-sentence summary. Turns out to be surprisingly useful. It's also fun as you can customize the speaking style and mirror your vibe etc.

The voice plugin gives commands to control it:

    /voice:speak stop
    /voice:speak azelma (change the voice)
    /voice:speak <your arbitrary prompt to control the style or other aspects>
[1] Handy https://github.com/cjpais/Handy

[2] Pocket-TTS https://github.com/kyutai-labs/pocket-tts

[3] Voice plugin for Claude Code: https://github.com/pchalasani/claude-code-tools?tab=readme-o...

raajg
I've been dabbling with STT quite a bit and built my own tool using Deepgram. But just tried Handy and it's SO FREAKING FAST! Love it.
srinifromsalem
For local speech-to-text, Whisper remains the gold standard - you can run it locally with good accuracy across languages. For speech-to-speech, you'd typically chain Whisper with a local TTS model like Coqui TTS or use something like Tortoise TTS for higher quality but slower processing. The key is balancing accuracy, speed, and resource usage based on your specific use case. If you're doing content creation workflows, consider what post-processing you might need - sometimes the raw transcription needs structure and enhancement beyond just accurate words.
mumbleflow
+1 on the post-processing point. Raw Whisper output is ~90% there but punctuation, grammar, and formatting are the missing piece.

I built MumbleFlow to address exactly this — whisper.cpp for STT plus llama.cpp for smart text cleanup, all running on-device. Metal/CUDA accelerated, sub-second latency on Apple Silicon. Global hotkey works in any app.

$5 one-time, no cloud, no subscription. https://mumble.helix-co.com

d4rkp4ttern
Hex is my new favorite STT on MacOS. Also uses Parakeet V3. I didn't think it could possibly be faster than Handy, but it is much faster - even long ramblings transcribed within a second. It's MacOS only, leverages the CoreML / Apple Neural Engine.

https://github.com/kitlangton/Hex

Also the transcriptions with hex don't seem to suffer from some of the issues with Handy, such as stutter.