#Speech
200
2026-09-09
Show HN: Sparrow-2 – Noise cancellation isn't designed for conversational AI
S
Hey there, I’m Brian. I've been shipping conversational models at Tavus for the past two years. I want to tell you about our latest audio-understanding/turn-taking model: Sparrow-2! It’s a new category of model and a unique new approach to conversational flow understanding. Earlier this year we launched Sparrow-1, (at the time) our SoTA turn-taking model. Since our Sparrow-1 launch, I’ve spent a lot of time listening to humans talking and trying to really understand how people know when to talk, when to listen, and when to wait. I’ve also been hunting down failure modes of the current SoTA models. And while Sparrow-1 is great, there are some failure patterns I see. We tried solving the problems with existing approaches, but solving one problem only created another. Current turn-taking models (like Sparrow-1) use noise cancellation to strip background sound, leaving only basic prosody and phonetic word cues to manage turns. Non-transcribable audio such as breathing, sighs, and environmental sounds provides critical context that humans use to hold or signal turn changes. This is because these models are primarily focused on verbal activity. Treating non-verbal audio as background noise discards vital conversational data, destroying the natural flow of dialogue. Now, with Sparrow-2, instead of modelling just the primary speaker’s verbal audio, we’ve trained a model with access to all the sounds and let it decide what matters and what does not when it comes to conversational flow. Our new model continuously streams in audio and is able to understand semantics, prosody, timing, speaker identity, sighs, breaths, back-channels, interruptions, background speech, and unintelligible audio with the goal of understanding what the agent should do given the state of the audio. Sparrow-2 recently ranked #1 on Sesame’s new Turnbench, but that’s only part of the equation when it comes to good conversation flow. Turn-taking is good for timing, but models should provide more information downstream especially in situations where noise impacts conversational quality. Sparrow-2 fits into our larger model family and is semi-duplex. For example if the user is in a room that’s too noisy, now the bot can ask the user to move to a quieter space. It also considers the timing of sound in relation to the AI speech as well as the user’s. This helps it to disentangle normal speech from interruptions and back-channels. Another added benefit of our approach to Sparrow-2 is to finally crack the cocktail party problem: how to have human-like conversations 1:1 in noisy environments, without losing the signals we rely upon for conversational flow. By allowing all sound to be learned, the model naturally learns to focus on what matters and transcends the rest. Noise understanding lets voice AI filter out background speech and ambient chaos, whether it's a kiosk in a noisy lobby, a shop assistant on a busy floor, or an interviewee in a cafe. When noise overwhelms the audio, the AI behaves like a human: it simply asks you to speak up, move, or swap mics. I’d love for you guys to give it a try and let me know what you think and feel. You can try it here: https://sparrow2.tavuslabs.org/ I also wrote up some technical details about the model architecture here: https://www.tavus.io/blog/sparrow-2
2026-09-15
Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost
A
Hey HN, Toby from Nari Labs here. We've been working on making OSS speech models super-fast. Last year, we built Dia, the first OSS text-to-speech model capable of doing natural dialogue. Since then, so many more great speech models have been released to the public. But the market is still dominated by closed source models. We think that's an inference problem. Existing systems such as vLLM / SGLang are not well suited for multimodal inference. To prove this, we built an inference engine specialized for Qwen3-TTS and open-sourced it ( https://github.com/nari-labs/nari-qwen3-tts). Running at sub-50 ms latency at 10 RPS, this showed open models can be run much faster and cheaper. Since then, we've been working hard to bring cheap, fast, and high quality serving to all. And we've even beat closed models at their game! Measured on the highly cited Coval (YC S24) voice AI benchmarks, our Qwen3-TTS endpoint not just is #2 in latency, but #1 in accuracy (WER) compared to 11Labs, Cartesia etc. while being the cheapest endpoint. Our Qwen3-ASR endpoint has the lowest latency and #2 accuracy, just 0.1% away from #1. It is the second cheapest model on the list. It took a lot of clever inference engineering to make these models quick, perform well while keeping costs low. Interestingly, Alibaba's official endpoints seem to perform worse in terms of accuracy and latency compared to ours. But nonetheless, much love to the Qwen team for OSS-ing these amazing speech models. We want to continue to push prices down to make speech technology a commodity - so that every app can have great TTS and STT without worrying about unit costs. We're also working on other parts of audio such as diarization - as well as video and world model inference. More to come!
2026-09-11
Show HN: Open-source simulation testing infra for voice agents
A
Hey HN, we’re Nischal & Naman. We’re brothers, and together we’re building an open-source platform for simulation based testing of voice agents (try it out in 5 mins - https://docs.egma.ai/docs/get-started/quickstart, 2 min demo video - https://youtu.be/wgDWEe5UAUY) Platforms that help you do simulation testing already exist. But they all charge a heavy premium on top of inference costs. We believe if the industry truly wants to scale simulation testing of voice agents, we need to stop charging a premium on inference and start providing infrastructure to scale simulations. The project is built in a way that allows you to bring your own STT, LLM, and TTS provider keys while also providing a way for us to provide inference directly within the platform at a 0% markup so you don’t have to wrestle with multiple keys/ rate limits. A bit on why’re we’re building this - We started working on voice agents in early 2024 and since then, have worked on numerous voice ai systems - like screenless voice-powered hardware for kids[1], AI receptionist deployed in healthcare practices like med spas & therapy clinics and personal accountability coaches. Some of these were full-fledged startups others were just side projects. But we kept on encountering similar issues all throughout. One of the most frustrating parts was calling the agent again and again, reciting the same script to test its behavior. We also kept on encountering new issues all the time in production that we couldn't have simulated pre launch. This frustration led us to a bigger question: how can developers trust the voice agents they’re shipping? We believe building that trust takes two things - - First, you need a way to test the major scenarios your agent will face in production before you release it, without having to make every call yourself. But you can’t test for everything. Real world is too messy to predict in advance. - Which brings us to the second: you need a way to find issues once your agent is in production, whether it’s handling a few dozen conversations or millions. Detect drift in known behaviors AND surface unknown-unknown ways in which your agent is going wrong. We think it’s a really hard problem to solve. And having felt it firsthand, we’re deeply motivated to take a shot at it. Today we’re launching the simulation testing side of the platform. We feel it’s mature enough that real teams can depend on it. For eval design, we took inspiration from anthropic’s evals design[2] and extended it to voice systems. For technical & business model design we borrowed ideas from Langfuse[3]. Our stack is postgres, clickhouse & minio. Its easy to self-host[4] & the code has a permissive MIT license. We also have managed cloud version. We’ve written more about our [testing]( https://docs.egma.ai/docs/core-philosophies/testing-philosop...) and [monitoring]( https://docs.egma.ai/docs/core-philosophies/monitoring-philo...) philosophy in the docs. We’d love feedback from the HN community and people building voice agents - how are you testing today, what’s working and what’s frustrating? We’ll be in the comments. Thanks! [1] https://x.com/theBhulawat/status/1966200231705595932?s=20 [2] https://www.anthropic.com/engineering/demystifying-evals-for... [3] https://github.com/langfuse/langfuse [4] https://docs.egma.ai/self-hosting/get-started
2026-09-25
Show HN: PlaceCall (YC W26) – agentic API to call businesses and get things done
A
Hi HN, this is Yarik and Vlad from VOYGR - we are building the tools for agents and apps to engage with local businesses. It all started with our own pain point at VOYGR: calling businesses to verify if they are open. We are both from Google (Maps and Search) and even there, the merchants and venues don’t keep this info updated. So we built an API and started using it in-house. On July 4th, we were driving through Portland looking for a place to eat. Google Maps was saying “Holiday hours may vary”. We tried some AI assistant apps (Poke was trending back then), and they couldn’t help. Our API found 15 Thai and sushi places and called it in parallel. A few confirmed that they are open today and are taking walk-ins. One was marked closed on Google. The app can find the restaurant, but someone has to answer the phone. This is the problem we kept seeing. Assistants can’t do much in the real world where the phone number is still a major communication interface. Muse added calls in beta mode, but it’s still calling only one place at a time. There are a bunch of tools to create your own voice agents, but nothing that can work simply out of the box. We’ve built PlaceCall to fit all your agentic needs. Give it a task in plain English and a US phone number (or a list of numbers) - it navigates phone menus, waits for you on hold, and returns a structured response with outcome, recording and transcript. If you don’t have a phone number, just describe what you need and PlaceCall comes up with the recommendations. Here is the demo: https://youtu.be/7ZbVCPv8Wq0?si=LoLxxx1M7nhS7_j- When PlaceCall API was tested in our hackathon, we had the following use cases implemented by the developers: checking if a doctor accepts new patients, getting quotes for car service, and running quick surveys. The API can be used through Claude Code and Codex; examples and setup are listed in the repo: https://github.com/voygr-tech/placecall We give the first 250 calls free. Product page is here: https://voygr.tech/placecall/ Try it and let us know how it goes. We are interested in learning what you would use it for and what is missing. We are here all day and happy to answer any questions. Our email: [email protected]
2026-10-01
lokutor-ai/oido
A
Oído: open-vocabulary speech recognition that fits in a $5 ESP32-S3. 3.7% LibriSpeech WER, no cloud, no NPU.
2026-08-26
oboroge0/hayamimi
A
早耳 - Real-time multilingual speech-to-text on CPU only. Live subtitles, browser dashboard, speaker labels, translation. No GPU, no cloud.
2026-10-13
Show HN: Atticus – Hold-to-talk voice assistant for macOS that runs on Claude -p
A
Hi HN! I'm Saarth. I'm in 9th grade, and I built Atticus. Atticus is a fast and cheap Mac assistant that can do tasks for you. You hold down Control-Option-Space, speak or type your task, be it complex or a simple browser search, and Atticus will get on it. The interesting part is that simple tasks, like opening apps, playing a Spotify playlist, or web queries, don't touch AI, and instead are processed locally and typically finish in under a second. For example, prompting Atticus to open apps takes around 0.08 seconds, sometimes even finishing before you finish your sentence, sort of like Jev. Any tasks that are more complicated will be sent to Claude via claude -p, meaning you never need an API key and Atticus will run on your existing Claude Pro or Max plan. By using this approach, costs are also cut down immensely, with, on average, tasks costing a fraction of a cent. To achieve Atticus' speed, it remembers shortcuts from each task it completes. When it does a task right for the first time, it saves its steps and replays them the next time without AI. For example, a workflow of creating a new meeting took about 30 seconds the first time around. Atticus then logs the exact steps to memory and takes 5-8 seconds on the next pass. To add to this, Atticus also learns about you as you use it more and from what's on your computer, including your name, your apps, and things you want it to remember, personalizing its answers to you. To combat the safety concerns over giving an AI unrestricted access to your device, Atticus has toggleable restrictions, so before anything is deleted, sent, bought, or written to a file, the user is prompted before that action. Some features I'm currently working on include a meeting copilot that capitalizes on Atticus' speed, allowing Atticus to listen in on meetings and answer questions in real time as they come in, personalized to the context of the meeting and what it knows about you. To run Atticus, macOS 26 or higher is required for its voice transcription features. The voice transcription is also done locally by macOS. Atticus is free, open source, and also very fresh, and I'm completely aware of its many rough edges, which is why I'd love to hear from everyone about what breaks and what you guys would like to see Atticus do!
2026-09-29
yfyeung/PrunedCTC
S
Memory-efficient CTC loss with exact loss and first-order gradient equivalence under vocabulary reduction, and activation memory that no longer scales linearly with vocabulary size.
2026-09-09
Omni-Interaction-Gander/Omni-Interaction-Agent
A
Open-source end-to-end omni interaction agent for natural full-duplex voice collaboration, continuous audio-visual perception, and asynchronous long-horizon agentic execution.
2026-09-07
xzf-thu/BreezeTTS2_Mac_Streaming
A
Real-time Breeze-TTS-2 streaming on Apple Silicon — RTF from ~4 down to ~1. mlx-audio 0.5.1's depth decoder recomputes each frame's existing acoustic codes instead of reusing its KV cache. Adds intra-frame KV reuse, one CPU read-back per frame, an optional compiled whole-frame path, and RTF/underflow stats.
2026-08-30
Show HN: SubSmith – Turn your own videos into language-learning material
A
I've been learning Japanese for a few years and kept running into a similar problem. I'd find a video I wanted to learn from, hear a useful sentence, and then realise that turning that sentence into something I could study later was both time consuming and draining at times. I would end up jumping between a video player, subtitles/transcription, a dictionary, screenshots, audio clips and Anki. So I built SubSmith to bring that workflow together. You can drop a video or audio file into it, generate a transcript locally and then use the transcript alongside the media to: * look up words and sentences * replay individual lines * edit the transcript * save useful sentences with their original context/audio * export them as Anki cards The important part for me is that it works with your own media. It isn't tied to a particular streaming service or library, so I can use the random anime episode, podcast, lecture, etc. that I'm actually interested in studying. It's an offline-first desktop app, and transcription happens locally rather than sending the media to a transcription API. I'm sharing it here because I'm now more interested in finding out where this workflow breaks down for other people rather than adding features randomly now that I have solid core/base. For example: * Would you actually save sentences from your own media? * Which part of this process feels like too much work? * Does having the audio/context attached make creating an Anki card more useful? * Would you prefer this to work inside your existing video player/browser? * Is installing a desktop app a significant barrier? * And does requiring an account before starting the free trial make you give up? The current version does require an account to start the trial, and I'm trying to work out whether that's meaningful friction for the people who would actually use this. It's free to try, and I'd particularly appreciate feedback from people who already learn languages through their own videos, anime, films, podcasts or other media. I'm the developer, so I'll be around in the comments to answer questions and discuss how it works. https://subsmith.app
2026-10-20
inclusionAI/Ming-3.0-tts
A
Ming-3.0-tts is an open-source TTS model family with 0.5B dense and 7.9B-A1.3B MoE variants, supporting multilingual speech, voice cloning, voice design, and natural-language control.
2026-09-18
HuskerMinion/techo5-dot
A
Linux firmware for the Echo Dot (2nd gen): no Fire OS, no Alexa. A local Home Assistant voice satellite with all seven mics, Bluetooth speaker mode, signed A/B updates and SSH.
2026-10-21
andrisgauracs/whistle-esp32
A
Whistle speech-to-text running fully on an ESP32-S3: hold a button, say a colour in one of 7 languages, the LED does it. No network.
2026-10-09
opennookorg/betterwispr
A
Free, open-source, local-first dictation app for macOS. Hold a shortcut, speak, and text is typed into any app. On-device speech-to-text with Whisper, Parakeet and Apple speech. Private, offline, open-source Wispr Flow alternative.
2026-09-25
Saekisui/binaural-voice
A
Make TTS voices speak right by your ear and walk around your head: KU100 near-field HRIR binaural rendering + position labels.
2026-09-22
nyrahealth/nyra-forced-aligner
A
Word and phoneme level speech timing for spontanoues speech. Fast, accurate and robust.
2026-10-01
Show HN: Parrot – Open-Source Smart Meeting Recorder with Co-Pilot on Mac
B
Hello Hacker News I am Uygar, I am an entrepreneur from London. I run my businesses on calls everyday, customers, partners and suppliers. And i have a horrible memory i forgot things. So months ago with the help of Claude i have built Parrot. I have designed and coded for my work and what i need. An to be honest worked very well and helped me alot. Parrot records what your mac hears and everything stays in your computer if you use local models, no account, no API calls. There is something called copilot which made my life easier, you can upload your files and when parrot hears that question on the screen recommends the answer. Which i believe very handy. If you want to make it smarter and dont mind cloud you can hook up your Claude API and Deepgram account, that gives super powers to Parrot. You still keep it locally but eventually you need to make API calls. So local or cloud totally up to you. Then after months of thinking i have decided share it as open source and this is my first open source project, so please go easy on me :) No account, no membership, open source and free. Code: https://github.com/turantekin/Parrot This project made me so excited and really would like to share with you guys so i hope can help you too. Again, i am new so go easy on me and if you have any feedback i would like to hear. Thank you Uygar
2026-11-05
aligh98/tts-director
A
Agent skill that directs scripts for TTS (ElevenLabs v3/v4 tags): rewrite for the ear, tag budget, free linter, A/B tester. | اسکیلی برای کارگردانی متن قبل از TTS: بازنویسی برای گوش، تگگذاری بدون زیادهروی، لینتر رایگان و تست A/B. فارسیمحور.
2026-11-02
iiinno/OpenHinoVoice
A
A Japanese voice input app for Windows. Recognition runs locally; formatting can be chosen from ChatGPT / OpenCode Go / OpenAI
2026-10-20
C4rohan/Lampline
A
Self-hosted voice agent platform: import your Dialogflow CX and CX Agent Studio agents, build and test them, and take calls on your own hardware. 20 model providers, phone and SIP through jambonz.
2026-10-17
christos-antono/NPCTalk
B
Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.
2026-08-29
SesameAILabs/turnbench
A
TurnBench: a multi-domain benchmark for end-of-turn and interruption detection in spoken dialogue
2026-10-16
Calvino-Y/mcd-mcvoice
A
McVoice · Visually impaired users complete the entire McDonald's ordering flow by voice (choose store → order → price calculation → checkout) · Entry for the McDonald's Programmer's Day creative development contest
2026-10-13
recepyagmur/EnglishPractice
A
Yerel, çevrimdışı ve taşınabilir İngilizce pratik uygulaması (Türkçe konuşanlar için): yapay zekâyla sesli/yazılı sohbet ve anında düzeltme, A1–C1 dersler ve sınavlar, Türkçe sesli öğretmen, kelime ve kalıp çalışma, YDS tarzı süreli testler. Windows ve Linux. Ollama + Gemma 4, Whisper, Kokoro, EMA Lightning.
2026-09-27
tgeczy/ssi263-speech
A
The SSI-263 speech chip, emulated, with the original firmware of the Speak-Out, Braille Lite, Accent-mini and Accent SA driving it. NVDA add-ons.
2026-10-10
lnenad/lipwise
A
Private voice dictation for Windows, macOS and Linux. Hold a shortcut, talk, and Lipwise types what you meant into any app: speech recognition runs on your computer, and an AI editor understands "scratch that", lists and rewrites. Works with local AI, Claude or OpenAI.
2026-09-22
oil-oil/video-editor
A
Smart general-purpose video rough-cut and slip-of-the-tongue/blooper removal Skill: automatically detects speech pauses and silence, uses a large model with concurrent sliding windows to identify slips and retakes, and exports a final cut with hardware micro-fades and no audio pops.
2026-09-18
HuskerMinion/techo5-spot
A
Linux firmware for the Echo Spot (1st gen): no Fire OS, no Alexa. A local Home Assistant voice satellite with a round touch face, camera, Bluetooth, phone calls and signed A/B updates.
2026-09-10
chenkb98/voxweave
A
Streaming speech language model plumbing: audio frames, turns, conversation schemas, batching, and adapters.
2026-10-13
vatavale/folivox
A
Turn any e-book into a chaptered audiobook in your own voice: free, local, CosyVoice 3, with optional online engines
2026-09-21
wquguru/dasheng
B
Read Aloud — R2T2 streaming ASR listening, Jev word-by-word judging, English reading scoring
2026-11-02
justhalfbit/thinksmart-ubuntu-image
A
Voice-assistant system image for Lenovo ThinkSmart View (CD-18781Y), based on rickx/ubuntu-thinksmart: boots straight into the voice UI; flashing guide in Chinese and English (for people and AI agents), image build scripts and device fixes | Voice-assistant system image for Lenovo ThinkSmart View (CD-18781Y), based on rickx/ubuntu-thinksmart: boots straight into the voice UI; flashing guide in Chinese and English (for people and AI agents), image build scripts and device fixes
2026-10-29
oxnw/ai-phone
A
A SIP phone daemon with local speech and language models on Apple Silicon.
2026-10-23
alexturkey/voxcpm2-turkce-ses-tasarimi
A
Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read Turkish text. Patched audio.cpp, local UI, 7 synthetic voices.
2026-10-22
Saganaki22/ComfyUI-Ming-3-tts
A
Native ComfyUI port of Ming-3.0-tts, supporting 0.5B and Tiny 9B speech generation.
2026-08-29
wavtechyukky/LeapSinger
B
Fast singing-voice acoustic model: harmonic + noise excitation refined into a mel by a 1-step rectified flow (bundled NHVSing vocoder). Multi-speaker + style control; ONNX/OpenUTAU export.
2026-08-23
Lexombien/lemyloi-dichvideos
B
Trình chỉnh sửa video local-first với ASR, OCR phụ đề gốc, dịch và thuyết minh.
2026-10-26
andrisgauracs/who-said-what
B
macOS app: drop a podcast or video, get a transcript with every line assigned to a speaker. On-device, built on Desert Ant Labs' Who + Apple's speech transcriber.
2026-10-07
canberk7/ema-lightning
B
Tiny, fast and accurate Turkish text-to-speech. 8.6M parameters, 0.92% WER on Freya-TR-Eval, first audio in ~4 ms and 1,300× real time on one GPU. Streams audio, batches many callers on one GPU, and runs offline on a GPU or CPU.
2026-10-04
mallahyari/nemotron-asr-streaming-farsi
B
Streaming Persian (Farsi) speech recognition: fine-tuning NVIDIA Nemotron 3.5 ASR streaming. Data prep, training, evaluation, inference.
2026-09-03
piyushxt43/sayszz
B
Your voice, at your cursor, in milliseconds. Free, open-source, 100% on-device dictation for macOS — Metal-accelerated Whisper, one-key hotkey, local history with stats. A Wispr Flow alternative that never phones home.
2026-08-23
ChenShuo2004/cs-board
B
A local AI tool that automatically generates whiteboard animation videos from a reference voice and Chinese script.
2026-10-16
FirmwareVersion/choravox
B
Offline multi-speaker meeting-speech toolkit: planted-ground-truth synthetic meeting factory, VAD, speaker embeddings, diarization (AHC/spectral/VB-HMM), overlap detection, CTC speaker-attributed ASR, cpWER/DER/JER evaluation, online streaming mode, deterministic reports. NumPy core, CPU-only torch extra.
2026-10-14
lcoutodemos/chums
B
Talk to Claude Code and Codex agents from an Apple Watch and an iPhone. Each agent is a character on the watch.
2026-10-28
dongtaowei54-sys/root-word-animation
B
English root-word memory short-video generator: one line + one ball turns a root into a 9:16 memory clip (design table → SVG animation → edge-tts → frame-by-frame rendering → five checks)
2026-10-23
JMS1717/ming-voice
B
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD Radeon GPUs (ROCm on WSL2)
2026-10-10
haiderfarooq3/khan-explainer
B
Claude Code skill: Khan Academy style explainer videos. A pen draws while a voice explains. Free, local, no API keys.
2026-09-28
heartmade-studio/skryba
B
Hold Fn, speak, and your words appear wherever you type. A small macOS dictation app using Groq's Whisper.
2026-09-24
wavtechyukky/PrettyPitch
B
A singing F0 model trained without scores — no note onsets, no note pitches, no reference score
2026-10-25
bruceleroyjr/hermes-watch
B
Talk to Hermes Agent from an Amazfit watch: voice in, answers on your wrist, Approve/Deny for Claude Code changes
2026-09-07
nixfred/omavoice
B
Voice recorder with live whisper.cpp transcription for Omarchy (GTK4, PipeWire)
2026-09-03
dogenthq/KorvaTTS
B
Vietnamese-first, on-device text-to-speech with code-switching (ONNX Runtime)
2026-10-24
alexturkey/crisperwhisper-turkce-kelime-zamani
B
Verbatim speech-to-text with word timestamps on a 4 GB GPU: CrisperWhisper 2.0 Turbo (CT2 int8) + wav2vec2 CTC alignment. Turkish-first, Linux/WSL2.
2026-10-16
PedroMarinhoDev/ComfyUI-Drama3
C
Fish Audio Drama 3 text to speech, natively in ComfyUI: voice cloning, dialogue and inline cues on cards from 8 GB, plus a native Qwen3-ASR. Built with Fish Audio.
2026-08-29
maisterr/phone-llm-fp8
B
FP8 quantization + vLLM serving of pipecat-ai/phonellm-alpha-1 on Modal
2026-10-29
floatboatai/OpenMinutes
B
OpenMinutes · voice recorder workbench: import · transcribe · AI categorization · search and review for MemoTalk S1 recordings (open-source implementation of Floatboat Workbench)
2026-10-16
mouse2p/echoparley
B
End-to-end spoken-dialogue framework: deterministic semantic speech units, unified interleaved token streams with turn-control tokens, a duplex turn-taking state machine with barge-in and latency budgets, deterministic session replay, and turn-taking evaluation on planted synthetic dialogues.
2026-10-15
qnguyen3/QUAN-Transcribe
B
Inference code for QUAN-Transcribe: fast Vietnamese speech recognition on EmbeddingGemma 2
2026-10-03
masonasons/SingingVoiceStudio
B
VocalWriter Studio rebuilt in C++ and wxWidgets, singing with VocalWriter, DECtalk, the SSI-263 and Microsoft Sam, Mike and Mary. Screen-reader first.
2026-09-30
Thesimpleex/steno
B
Free, open-source dictation and meeting notes for macOS. Hold a key, speak, and your words appear at the cursor – transcribed locally with OpenAI Whisper.
2026-09-25
jankeesvw/omarchy-meeting-recorder
C
Record meetings on Omarchy: mic and computer audio as two tracks, transcribed on your own machine, with speakers, chapters and a player.
2026-09-09
Turbo1123/Turbo-IO
B
Unofficial SDK and iOS client for RayNeo iO: non-commercial study and research, voice AI, recording, custom notifications, Codex, and Web display preview. BES2800 lightweight glasses, Android pending development.
2026-09-01
tianyupaipai-cmd/pai-voice
B
A self-hostable, model-agnostic realtime voice layer for personal PWA and terminal agents.
2026-10-17
plotarmordev/drama-tensorfold
B
Fish Audio Drama 3 text-to-speech on the TensorFold native CUDA engine for DGX Spark (GB10): recipe, engine patches, benchmarks. Built with Fish Audio.
2026-10-13
knowledgefxg/Transyt
B
Turn a YouTube video or a local file into a subtitled video on your own computer, and keep the Chinese and English subtitles, transcripts, and vocabulary so you can study with the picture.
2026-10-13
michaelpersonal/foresight-zh
B
Chinese transcription for Google AI Edge Foresight on macOS via a DYLD-injected shim (no app modification)
2026-10-04
Malmen877/prata
B
Prata: lokal svensk tal-till-text i webbläsaren. Local, private Swedish speech-to-text.
2026-11-05
aws-samples/sample-multilingual-ivr-contact-center-for-amazon-connect
B
Deploys a multilingual IVR contact center on Amazon Connect with one AWS CDK stack: caller identification, per-agent case isolation, returning-caller routing, supervisor case assignment and voicemail-to-case with Voicemail Express.
2026-10-09
anurag12-webster/rapido-tts
B
Tiny, fast Brazilian Portuguese text-to-speech (21M params)
2026-09-25
malhashemi/opencode-gpt-live
B
Talk to OpenCode out loud: real-time GPT-Live voice calls on your ChatGPT subscription
2026-09-07
trypsynth/evvdroid
B
Eloquence text-to-speech engine for Android and Wear OS, built on openevv
2026-08-23
iamcheyan/omarchy-voxtype-enhance
B
An Omarchy Voxtype enhancement plugin with automatic offline model downloads, multilingual voice-input settings, and terminal-aware universal paste.
2026-11-09
MithrilMan/voice-workshop
B
Interactive, physically based simulator of human voice production in the browser: a buzz, a hiss and a filter
2026-10-26
alexturkey/dubworld
B
Local-first AI video dubbing pipeline: transcription, translation, speech synthesis and timing alignment.
2026-10-19
urusaqqrun/jarvis-voice
B
JarvisVoice: automatic voice input and control (macOS menu bar app). It listens automatically while running and writes what you say into the app you're using; open AI cleanup from the menu (OpenAI/DeepSeek/Claude, like Typeless), auto-find input fields, and control apps with voice commands.
2026-10-15
grigio/sonia-assistant
B
Sonia - Local Voice Assistant in less than 13GB of RAM, TTS/STT, No Dedicated GPU required, Skills supported
2026-09-25
yukitorido/short-video-generator-AI
C
AI video processing pipeline for generating vertical shorts using LLMs, Whisper transcription, highlight detection and automated editing
2026-09-17
TigerSHe1998/Moss-Transcribe-WebUI
B
A local high-performance speech transcription WebUI based on transcribe.cpp + Moss-Transcribe-Diarize.
2026-11-06
majorminorlabs/hermes-voice
B
Talk to a Hermes Agent profile through Home Assistant Assist
2026-10-09
kadirnar/drifting-tts
B
One-step Turkish text-to-speech trained with a drifting objective (Kyutai learned-temperature recipe)
2026-10-05
Corvelis/irodori-tts-coreml
B
Community Core ML runtime, Swift SDK, and iOS/macOS samples for Irodori TTS v4.1 Small MF.
2026-09-15
FelixQiu1/XiaoAi-LLM-Router
B
Upgrade an old XiaoAi speaker into a DeepSeek/Ollama smart assistant with one click, zero hardware mods. | Upgrade your XiaoAi speaker to a DeepSeek/Ollama AI assistant with one click. Zero hardware mods needed.
2026-09-14
vanch007/mlx-AuK
B
AuK: Native Apple Silicon MLX Port for 1.5B Speech Foundation Model (TTS, Vocal/Content Edit, Enhancement & Separation)
2026-09-08
maverickgao8848/kouyu
B
A guided English speaking practice Skill with gentle correction and a local review workbench
2026-09-03
zeroa234/ryza-ai-revive
B
Offline fan-made Ryza AI companion. Bring your own LLM/TTS. 离线同人莱莎 AI 陪伴，自填大模型与语音。
2026-08-28
cuppibla/live-dj
B
Talk to Mira, a late-night radio DJ you can interrupt. A live voice agent built on the Gemini Live API with the raw google-genai SDK — no framework.
2026-11-04
owenliu0924/Miyoria
B
An autonomous AI VTuber for Discord. She chats, joins voice, sings song requests, plays Minecraft and goes live, and she decides what to do herself, inside the guardrails you set.
2026-10-24
samyeei/mosaico-learning-assistant
B
ESP-Mosaico study assistant: photograph a question and pick one, voice follow-ups, step-by-step explanations. Source code public, commercial use prohibited (PolyForm Noncommercial 1.0.0). Legacy ABI 1 firmware.
2026-10-16
juinwei7/Shiyin
B
macOS meeting notes: live transcript, local transcription (Breeze ASR / whisper.cpp), speaker diarization, AI meeting notes with timestamps
2026-09-18
nirbhay41120003/EchoMind
B
Local-first voice memory assistant — capture speech, transcribe live, and ask a private RAG chatbot grounded in what you've actually said. No cloud required.
2026-09-17
davidmokos/expo-gpt-live
C
Expo SDK 57 voice app with GPT-Live 1 and AI Elements Persona.
2026-09-10
fufuchiu/speechloom
B
End-to-end speech model research: waveform encoding, causal decoding, codec tokens, joint losses and streaming.
2026-09-10
tosya301/midori-companion-avatar
B
Unofficial, non-commercial fan project for Mingqian Nailv: a local web AI Companion Avatar supporting audio lip-sync, dynamic character art, floating icons, lyric visuals, and generic Agent integration
2026-10-29
eriktaveras/pana-companion
B
La cara y la voz de tu agente de IA en una pantalla redonda de Waveshare (ESP32-S3 AMOLED 1.75 · ESP32-P4 4C). Hermes Agent, Whisper, Piper. Personalízalo con Claude Code.
2026-10-29
yanyan1115/ringringring
B
Zero-cost AI phone calls over free SIP: native iOS calls, no Mac/developer account, no need to buy or write an app.
2026-10-17
dakcoe/ezrite
B
A Mac · Windows app that takes notes during lectures, translates them into Korean, and explains unfamiliar scenes by pointing at the screen
2026-10-12
KorenKrita/simul-subtitle
B
Android real-time live subtitle translation: recognizes Japanese/English on the phone, translates into 22 languages with Index-Translate, floats over any app · Live on-device subtitles for Japanese/English
2026-09-20
okinaaudio/live-jev
B
Control Ableton Live with one short sentence (Japanese / English). Summon with ⌘⇧Space, type or dictate, done.
2026-09-15
KnowClip-ai/knowclip
B
Automatically cuts long videos such as livestreams, courses, talks and talking-head videos into highlight clips | local speech recognition, audio never leaves the machine; LLM picks the highlights, batch export
2026-09-10
howervoo/speechturn
B
A speech large model research toolkit: audio instruction data, acoustic adapters, CPU micro training and inference, streaming events and evaluation.
2026-08-23
Colin0512/interview-assistant
C
AI-powered speaking assistant for interviews and oral exams
2026-11-05
wyj5114/laobi-shike
B
老哔拾课: turn Bilibili course videos into reviewable, searchable, conversational notes. You deserve it. Song Hao's 108h video, parsed in three hours with notes generated for every section
2026-10-27
JeensLab/AI-Companion
B
Oleg — an AI companion for Minecraft 1.21.1 and NeoForge. Conversation, voice, mining, crafting and survival together.
2026-10-22
llm-xiaoye/douyin-to-obsidian
C
A portable /dy skill for cc-connect + Claude Code: Douyin videos, image posts and collections to Obsidian, with local ASR/OCR and private configuration.
2026-10-19
RegeneratusLabs/physical-hermes
B
Physical Hermes - Give your Hermes Agent a body. This turns a cheap AliExpress AI robot toy into a voice device for Hermes Agent — running entirely on your own machine, using your own model, with no vendor cloud in the loop.
2026-10-02
Cuongyd196/whiteboard-video
B
Biến chủ đề, kịch bản hoặc file SRT thành video vẽ tay bảng trắng hoàn chỉnh: AI agent viết kịch bản, tạo giọng đọc tiếng Việt (Vbee/Edge TTS), phân cảnh, vẽ nét bút liền mạch, gắn phụ đề và xuất MP4.
2026-09-21
kubeden/gps
B
GamepadSpeak: controller-triggered voice-to-chat for WoW Forever (addon + cross-platform helper)
2026-09-16
Steven-Tibbs/beckon
B
Voice control for Omarchy, powered by the Gemini Live API. Talk naturally; it acts while you're still speaking.
2026-08-27
Saganaki22/ComfyUI-Breeze-TTS-2
B
Breeze TTS 2 nodes for ComfyUI: voice clone, voice design, and voice direction with bilingual (EN/ZH) speech, inline vocal events, INT8 ConvRot quantized builds, and full ComfyUI / AIMDO dynamic-VRAM integration.
2026-08-24
imaketech1/YapJail
B
A Discord bot that puts users in "yap jail" - preventing them from speaking in voice channels and chatting while allowing camera and screen sharing!
2026-11-07
monoradio102/myradio
C
A broadcast station where characters read the news every morning, with just one GitHub repository. Model station: Monorail.
2026-10-29
dseditor/minimax-h3-colab
C
MiniMax H3 + ComfyUI on Google Colab (L4): basic notebook and talking digital-human notebook
2026-10-09
bariskisir/ema-lightning-api
C
Self-hosted Turkish text-to-speech API. One container, full and streaming synthesis.
2026-10-09
rcell233/pl-flow
C
PL-Flow: a two-stage, reference-conditioned text-to-speech model producing 32 kHz mono audio.
2026-09-19
trungdq88/youtube-sponsor-detection
C
Detect youtube sponsor segment with live audio and transcript powered by Jev
2026-10-09
ozcancelik/ema-lightning-web
C
Türkçe TTS modeli EMA Lightning'in ONNX ile WebGPU ve WASM üzerinde tamamen tarayıcıda çalışan sürümü.
2026-10-02
MultiX0/orion
C
A little voice assistant for your desk that you build and own. Flash an ESP32-S3 board with one double click and bring your own keys.
2026-09-28
animede/Realtime_Conversation_Video
C
Speak into the mic, and the character answers back in real time — with voice and video.
2026-09-20
KamiKitsune420/ms-sam-mike-mary-decomp
C
Microsoft Sam, Mike and Mary (SAPI 5) rebuilt in portable C, sample-accurate, plus the SAPI 4 voice effects (Hall, Stadium, Space, RoboSoft, Whisper)
2026-09-10
kunpengtalk/OmniStudio
C
OmniStudio is an all-in-one local large model desktop workbench (Electrobun + React), combining a model marketplace for downloads, inference management for the three engines llama.cpp/vLLM/SGLang, and four major applications — chat, voice, images and OCR — all local-first.
2026-10-28
moonoops/Droy
C
An Android AI Agent built on DeepSeek Harness, with Android Use tools, voice and a cat companion.
2026-10-25
varsian/ghost
C
GHOST Community Edition - local, realtime Live2D digital human plugin stack for DeepSeek Harness (DSH), with VoxCPM 1.5 TTS.
2026-10-07
mushigaite/short-video-maker
C
A free open-source project designed to turn youtube-videos into viral short videos. Highlight detection, subtitles, translation, voiceover, all in one for your content: no pre-clip credits or any watermarks. Designed for creators who want an alternative to short-video SaaS tools like OpusClip or Vidyo.ai for free.
2026-10-04
hyj-STAR/voiceshell-muse-bridge
C
VoiceShell · Experimental Muse bridge: ESP32 pairing, Linux text round trips, real walkthroughs and compatibility notes.
2026-09-17
OJY-lawyer/zhimu-player
C
Zhimu Player — Windows video player with subtitles and timestamped AI guides. ChatGPT web, DeepSeek API, Tingwu ASR. A bilingual Chinese-English video reading workbench.
2026-08-31
jia-seed/midi-voice
C
u can just hack your midi on a saturday night where you're feeling existential and also you still don't know how to do loops with the looper thing on it so you just wanna do it all with your voice
2026-10-16
kevinbadi/claude-codes-influencers
C
Build a talking mascot that turns any script into a lip-synced vertical video. Fork, add your mascot's art + a voice, post.
2026-10-02
openmimir/openmimir
C
Talk to all your coding agents. One hands-free, full-duplex voice conversation over Claude Code, Codex and OpenCode. Runs on your Mac.
2026-09-24
tjxj/qwen-audio-studio
C
Local web studio for qwen-audio-3.1-tts-next with secure macOS Keychain credentials and verified audio output
2026-09-18
thinkthank92/gemini-transcribe-mac
C
A real-time AI voice transcription & smart notes desktop app for Mac based on Gemini 3.5 Transcribe
2026-09-16
CtrlcvMaster/HearMe
C
This is the first project I have released. It is mainly designed to assist hearing-impaired individuals and includes features such as speech-to-text, voiceprint recognition, web screen casting, cross-app screen reading, cross-app captions, and more. /This is the first project I have released. It is mainly designed to assist hearing-impaired individuals and includes features such as speech-to-text, voiceprint recognition, web screen casting, cross-app screen reading, cross-app captions, and more.
2026-09-07
shinshin86/svg-aituber-chat
C
A local-first React demo for chatting with an animated SVG avatar, featuring TTS, lip sync, visual effects, and YouTube Live comment replies.
2026-08-25
LYiHub/pub-ai-inputs
C
Turn headphones, remotes, watches, game controllers and even cars into voice input devices better suited to Vibe Coding!
2026-10-17
ahmedbadr-dev/voice-ai-assistant
C
Python voice AI assistant: microphone STT, Google Gemini answers, offline TTS with pyttsx3. Clean env-based setup.
2026-10-15
Keith-Tseng/YiSheng-Live
C
譯聲 Live | Windows offline Chinese-English speech translation tool, executable download and full usage instructions.
2026-10-07
MediaPublishing/ainauten-voice
C
AInauten Voice: lokale Diktier-App für macOS. Quellcode, Screenshots, Video und Installation mit einem Agent.
2026-09-30
vakovalskii/nd-video-studio
C
Explainer videos from HTML (HyperFrames → MP4) with AI narrator, music and mixing — Claude Code / Codex skills on NeuralDeep models
2026-09-18
Show HN: AutoBot – live voice control for long-running AI work
C
I wanted to manage long horizon agentic workstreams via voice, then put my phone down, and have a harness manage completion - extending into full computer use. I was trying to build a personal Jarvis, so I benchmarked AutoBot to see how close I could get: - OSWorld: 32.41% (moved Sol Max from 4th to 1st, beating Opus 5) - AssistantBench: 50.70% Hermes and OpenClaw, but without needing a weekend and VMs. And with the ability to manage deep personalization AND keep strict privacy rules, storing data on encrypted disk. AutoBot is a passion project that grew out of trying to make this all work for myself. I’m sharing it here because I suspect other here have the same frustration. And I’m curious what else everyone is doing for this. It’s an MIT-licensed harness that lives within a project. Native voice lets me discuss tasks, check progress, and steer work; a local ledger tracks unfinished outputs and the evidence needed to call them done. Memory drives more autonomy over time, and defrags and locks in learning nightly while a heartbeat system persists execution. I’m not selling anything. If you’re building something similar for yourself, I’d love to compare notes. GitHub: https://github.com/demeyer1/Autobot
2026-11-02
kentjuno/chanh-dien-online
C
Chánh điện online 2.5D + bộ overlay TikTok LIVE (Node, Edge TTS). MIT.
2026-11-02
zane-tv/tiktok-live-temple-rpc
C
Chùa Linh Ứng Online — TikTok Live RPC 9:16 Interactive Buddhist Temple (Bun.js + ZeroTTS)
2026-10-29
jacke-pp/open-yoki
C
An AI live-stream host that runs on one server: voice, face, chat, memory, posts. The base yoki runs on. By Jacke_pp · contact: DM @Jacke_pp on X
2026-10-26
Esmerubphire/astrbot_plugin_feiyu_voice
C
AstrBot plugin and local HTTP service for Feiyu TTS, RVC v1 and optional score singing
2026-10-25
coder-irwin/voice-agent-workshop
C
🎙️ Local, open-source voice agent that talks back AND acts (opens YouTube, searches, scrolls). Workshop starter: whisper + ollama + kokoro + playwright
2026-10-19
joeseesun/lexfridman-cn
C
Lex Fridman Podcast Chinese companion site: full catalog of 506 episodes, AI Chinese deep-reads, official audio/transcripts and full-text RSS | Chinese companion to the Lex Fridman Podcast: AI deep-reads, official audio & transcripts for all 506 episodes.
2026-10-01
Dubly-AI-Gemini/dubly-AI
C
Real-Time AI Dubbing & Youtube, Live Translation for Videos, Live Streams & Games Dubly AI is a Chrome extension for real-time AI voice dubbing and live translation of online videos, live streams, streaming content, and gameplay. Powered by Google Gemini, Dubly AI translates spoken content in real time and generates AI-dubbed audio in your preferre
2026-09-17
ustoppble/openjarvisbr
C
OpenJarvisBR — assistente de voz open source em Rust com Gemini Live
2026-09-11
FjgarciaMac/WhisperDeck
C
On-device audio transcription toolkit - trim, tag, transcribe and export recordings locally, with a Python engine and an Android demo app.
2026-09-11
Oruk-AI/orukeet
C
Orukeet: multilingual ASR with fitted, frozen Gabor kernels and native inference
2026-10-26
Liuzilu0913/ActionScribe
C
🤖 An AI-driven meeting action-item assistant using LangGraph and Groq, realizing the workflow from meeting to action. Automatically transcribes audio, extracts tasks, syncs to Feishu Bitable or sends group notifications.
2026-09-14
binghe1980/new-media-analyzer
C
New media analyzer: Douyin, WeChat official account and Xiaohongshu content collection, local transcription, data charts and AI analysis. Mac / Windows ZIP, personal non-commercial use only.
2026-08-24
richlearntodo-debug/vibe-flow
C
Vibe Flow is a low-cost Vibe Coding tool built specifically for Windows. Just connect a Bluetooth voice remote to quickly do Chinese and English voice input, code descriptions, and AI commands by hold-to-talk, with no need to buy expensive professional equipment. Let inspiration speak the moment it comes, and truly turn natural language into efficient development productivity.
2026-09-27
AnaaySampat/jarvis
C
Voice assistant for Android that controls your phone and PC. Say "Hey Jarvis" to chat, run tasks, operate other apps hands-free, or drive your Windows PC remotely. Built with Tauri 2, React, TypeScript and Kotlin. Experimental fan project.
2026-08-24
kerwinyoung77/OpenNomi
C
An expressive AI companion client for iPhone, built with SwiftUI and the Xiaozhi protocol.
2026-10-26
accomplish07zrh-eng/dsh-aurabot-qq
C
DeepSeek Harness plugin: lets AI live in QQ as "Big Fat Fish" (SnowLuma / OneBot v11). Expressions, voice, memory, space, Bilibili, covers, image generation are all modular — can be turned off, swapped, or extended locally by yourself, and even group chat strategy, prompts, replies and models can be changed, taking effect on save.
2026-10-26
cyber-xiaoya/cyber-xiaoya-live
C
Cyber Xiaoya Live Edition · component-based digital human (Vidu s2) · free and open source AGPL-3.0 · Author: 天工开帧 (same name on Douyin/Bilibili/YouTube)
2026-09-30
LindseyZ1205/video-processing-pipeline
C
Spring Boot service that transcribes uploads asynchronously: S3 presigned upload → S3 event → SQS → idempotent worker with DynamoDB leases, retries and a DLQ. Tested against LocalStack with Testcontainers.
2026-09-25
cclank/jevclip
C
Jev-powered video highlights and cited summaries from subtitles and scripts
2026-10-22
wave2234/ai-call-screen-share
C
See yourself on the call: voice calls, screen sharing and camera for a self-hosted AI (Android wrapper edition)
2026-09-19
phoiex/AAAAGENT
C
Live2D companion with voice, emotional memory, WeChat, and Codex / DeepSeek Harness. macOS-first; Windows in development. Noncommercial only; attribution required.
2026-09-14
steverhysjenks/HA-multilayered-LLM-Voice-Assistant-intent-local-cloud-
C
Logic-based multi-LLM voice router for Home Assistant, combining native intents, local Qwen, GPU-aware desktop Ollama, and cloud AI with intelligent fallback.
2026-10-26
zeekk0/OpenSakura
C
OpenSakura: MekaHime's first AI companion, open source. 3D VRoid avatar, real-time voice, emotion state, OpenRouter or Ollama brain.
2026-10-11
Show HN: A functioning Celery Man computer
D
Hi HN! It dawned on me that the latest AI models (Minimax H3 Max / Audio, GPT-6 Luna) can finally recreate the computer from the classic Tim & Eric Celery Man sketch. I spent a few days creating it: it has 100% parity with the original script, plus anything you ask for (doggy woof woof man or potato boy). Happy to answer any questions about the pipeline!
2026-09-19
moritzkremb/jev-voice-browser
C
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
2026-08-27
alphaparkinc/genpark-word-level-timestamped-phoneme-audio-transcriber-skill
C
Word-level timestamped phoneme audio transcriber (WhisperX style)
2026-10-23
Sanpan53/voice_agent
C
Multi-agent voice shopping assistant backend (FastAPI + AgentScope)
2026-10-12
Corvelis/dots-bridge-kit
C
A local bridge connecting your ChatGPT Dot to apps and devices through text, speech recognition, and voice-call APIs. Includes an Even G2 app.
2026-10-07
sanqianzilanyue/ai-voice-breath-kiss-water-2
C
From a single voice clip to a phone call — the AI lover's voice, advanced edition: why a sentence gets said twice, why pitch jumps in steps, how to add more panting without sounding acted, how to measure speech amount, and how to avoid repetition. ElevenLabs v4 + ffmpeg + whisper, all hands-on tested. Author: Li.
2026-09-20
brudarko/jev-mac-voice
C
English full-duplex voice control for macOS with OpenAI Realtime, native Accessibility, and Jev.
2026-09-20
kevinbadi/jev-voice
C
Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.
2026-09-14
Eyeing0721/deepseek-tts-unlocker
C
Unlock the official Read-aloud / TTS entry on the DeepSeek web version · Unlock the Read-aloud (TTS) button on chat.deepseek.com for accounts outside the grey release
2026-10-13
techgptx/Playlist
C
🎙️ JARVIS AI Voice Assistant for Android (Parts 1–7) | Gemini Live, Vosk & Automation.
2026-10-12
jkjkiiiii/mcdinner-mate
C
Eating alone, but not lonely. A voice dining companion Skill based on McDonald's MCP — not just ordering, but someone to accompany you through the meal.
2026-10-11
vibeeval/receptionist
C
Private source backup of the Apache-2.0 phone receptionist core and Turkish local dashboard.
2026-09-18
Akshayykadam/PixelBoard
C
Unlock Google 11's Gemini "Rambler" Natural Voice Dictation & AI Writing Tools on ANY Android phone. No root required.
2026-10-01
bayuewind/Muse-desktop-pet
D
Muse desktop pet: native macOS status monitoring, text and voice input, multi-format reply receiving
2026-08-24
bahmad-blip/SkyStar-AI
D
🌟 SkyStar AI - Pakistani AI Assistant by Sahil Ahmad - Voice, Chat, Weather, News, Image Editor - Professional Desktop App
2026-10-31
EntranceStarfish/VoiceStudioV2
D
Local AI voice studio: real-time voice changer, text-to-speech, voice cloning & dubbing with a drop-in OpenAI-compatible API. 100% offline, no cloud, no API keys. Unofficial fork of VoiceStudio.