Smallest.ai
Voice AI Suite for Enterprises
838 followers
Voice AI Suite for Enterprises
838 followers
Our conversational AI agents talk, text, and email your customers for you. Super fast and super safe. They work right inside the tools you already use. No messy add-ons, no data leaks. Just smooth, fast help for every customer.
This is the 3rd launch from Smallest.ai. View more
Lightning V3
Launched this week
Introducing Lightning V3 — Smallest AI's most advanced text-to-speech model. With 100ms latency, a 3.89 WVMOS score, and support for English, Hindi, Spanish, Tamil and 15+ languages, V3 was preferred over OpenAI's GPT-4o-mini-TTS by listeners 76.2% of the time.
Get audio output in 44.1 kHz and powers voice assistants, IVR systems, content creation and conversational AI with human-like speech. Instant voice cloning from just 10 seconds of audio. Real-time. Expressive. Enterprise-ready.
Free Options
Launch Team / Built With
Smallest.ai
Hey Product Hunt!
Lightning V3 delivers 100ms latency at 20 concurrent requests. That's real-time voice AI that actually scales. In blind listening tests, listeners preferred it over OpenAI's GPT-4o-mini-TTS 76.2% of the time, with a WVMOS score of 3.98.
But speed means nothing if it sounds robotic. Lightning V3 scores 3.33/5 on intonation and 3.07/5 on prosody; meaning it doesn't just read text, it speaks with natural rhythm, pauses, and expression. The kind of voice your users won't realize is AI.
It supports 15+ languages with more being added regularly (Indic & European languages included). It handles voice cloning from just 5-15 seconds of audio, and gives you flexible streaming via HTTP, SSE, or WebSocket. Whatever fits your stack.
We built this for developers shipping voice assistants, conversational AI, IVR systems, customer support bots, and anything that needs immediate, human-sounding voice feedback. Whether you're a solo builder or an enterprise team, the API is simple and the docs are solid.
We've been heads down on this for a while and we're genuinely proud of where V3 lands. Would love for you to try it and tell us what you think!
Tobira.ai
@ronitsoin 100ms latency is the number that actually matters for voice agents. You can have perfect prosody but if there's a half-second gap before the agent responds, users feel it immediately.
Congrats on shipping V3. Curious how the latency holds under bursty traffic - 20 concurrent is clean in tests, but real production tends to spike in weird ways. Do you have data on tail latency (p95/p99)?
@ronitsoin Excited to hunt this! Many congratulations on shipping this! The 100ms latency at scale is honestly impressive, that's the kind of performance that actually makes voice agents feel responsive instead of clunky. Well done! :)
Interesting positioning. A lot of TTS products talk about sounding natural, but for voice agents the latency piece is just as important as the voice quality itself.
100ms is the part that really caught my attention here.
How much of that performance holds up in real production settings once people add full conversational pipelines around it?
Smallest.ai
@luca_ardito That's the right question! Isolated TTS latency means nothing if the full pipeline adds 500ms on top of that.
That's why we built the entire stack in-house: STT (Pulse), LLM (Electron), and TTS (Lightning), all under one roof. When you stitch together 3-4 vendors, every handoff adds network hops, serialization overhead, and unpredictable tail latency. With an integrated stack, data moves between models without leaving the pipeline.
Pulse STT hits 64ms time-to-first-transcript. Lightning TTS hits ~100ms TTFB. These aren't benchmarks from different vendors hoping they'll add up nicely. They're co-optimized to run together. The full agent pipeline on our voice agent platform (Atoms) stays well under the conversational threshold where users start noticing gaps.
GrowMeOrganic
Super cool. Any plans for regional accents within languages (like Indian English vs US English)? I can use it for my SaaS tutorials.
Smallest.ai
@iamanantgupta Absolutely! Here are some of my top V3 voice reccos to check out! There are some Tamil accent voices too!
Does it support emotion control via API? Like being able to dial up/down expressiveness depending on use case?
Smallest.ai
@zerotox Hey Abhishek!
We're working on the emotional tagging feature! Coming out soon :)
Hi Guys, do you have a published comparison vs eleven for conversational use-cases?
Smallest.ai
@chintant Hey Chintan,
Yes, we did a deep dive on how the current system for Voice Evals is dead! You'll find comparisons against Eleven, Cartesia and OpenAI. Sharing you a link to the article.
Preety cool... How you guys are balancing low latency vs prosody quality, since expressive speech usually needs more context?
TTS for voice agents has a different bar than TTS for content - it's not just naturalness, it's latency under real conditions. An agent that pauses 800ms before responding feels broken even if the audio quality is great. Curious how Lightning V3 handles the tradeoff between quality and time-to-first-audio in streaming mode.