Pinned Tweet
Introducing Gnani Prisma v3.0, built for Indian calls that switch between Hindi, English and Kannada in a single sentence, run over busy streets and weak connections, and use brand names a model was never told about.
#GnaniAI #PrismaV3 #SpeechRecognition #IndianLanguages #ASR
This video deserves it's own credits section:
💡 Idea by: the entire star cast of real Indian calls.
⭐️ Starring: Hindi, English, Kannada, Bengali, Marathi (often in the same sentence) along with @pantinarajesh @OmJoshiOnX @Markiv093 @asqarsagsibil @5xAnime1 @shubhamsureka98 @pratikkat8 Shivam Saxena @Vijay_prasad @NajfeeHyder.
👊 Supporting cast: traffic, crowds, bad networks and brand names that never got a briefing.
✍️ Transcribed by: Prisma v3.0 🎬
Prisma v3.0 is live and you can run it today.
Sign in at app.gnani.ai and you'll find it in the speech-to-text console.
Introducing Gnani Prisma v3.0, built for Indian calls that switch between Hindi, English and Kannada in a single sentence, run over busy streets and weak connections, and use brand names a model was never told about.
#GnaniAI #PrismaV3 #SpeechRecognition #IndianLanguages #ASR
Launch Series : Day 10/10
Introducing scenario-based prompting in Gnani AI's Agent Builder. The agent gets the instructions for the step it is on, so token usage and latency stay low as the conversation grows. Link in the comments.
#VoiceAI #AIAgents #AgentBuilder
Launch Series : Day 9/10
A phone call usually gives you words. Nothing to look at, nothing to scroll back to, nothing to tap on.
But some moments need more than talking, a menu to pick from, a confirmation to glance at, a step that’s easier shown than said. Our AI voice agent on WhatsApp handles exactly that: it carries the call like any other, and the instant something’s easier to show than say, it lands straight in the same chat, no separate app, no “check your email.”
The call and the chat aren’t two channels. They’re one conversation, working the way a conversation should.
#VoiceAI #ConversationalAI #WhatsAppBusiness #CustomerExperience #Gnani #AIAgents
Launch Series : Day 8/10
Introducing Gnani AI Agent API.
Build and manage voice agents from your own platform, connect existing workflows, and bring conversation data back into your systems.
Explore more in our blog.
#GnaniAI #VoiceAI #AIAgents #EnterpriseAI
Launch Series : Day 7/10
Introducing Agentic Evals by Gnani AI, built to make sure every agent is ready before a real customer calls.
Agentic Evals runs simulated conversations and edge cases designed to break the agent, and scores each one out of 100. Below 80, an agent doesn't go live.
Teams cut QA time by roughly 90%, with a record of everything checked before launch.
Learn more in our detailed blog. Link in the comments
#VoiceAI #AgenticEvals #EnterpriseAI #AIAgents #AITesting
The funnel confirmed it. 62% of the drop-off between Contacted and Completed traced straight back to that one step, Document Verification Delay.
One Topic, one confusing step, one fix, instead of a guess.
Launch Series : Day 6/10
Introducing AI Insights, built to help enterprises understand their customers and the context behind what they ask.
#VoiceAI #AIInsights #EnterpriseAI #CustomerExperience
Launch Series : Day 5/10
Excited to announce: Gnani AI is now live in Japan and the UAE.
Our full agentic stack runs inside each country, from orchestration and inference to data and integrations.
Voice, chat, text and email. No conversation data leaving the territory.
Learn more in our detailed blog. Link in the comments.
#VoiceAI #DataSovereignty #Japan #UAE
Launch Series : Day 4/10
What does it take to build a language model that serves India in its own languages?
1.27 trillion tokens of continued pretraining. A vocabulary extended with 32,000 Indian-script tokens. And research into what happens when benchmark scores improve while answers drift into English.
Our new white paper documents the research and engineering behind Gnani Evon v3.3, the experiments, fixes and trade-offs across the full training pipeline.
Read the full white paper: gnani.ai/resources/research/…
hashtag#GnaniAI hashtag#SovereignAI hashtag#LLMResearch
Launch Series : Day 3/10
Every laugh and pause in this video was generated by our AI model.
This is Timbre 3, our new text-to-speech model, live today on the Gnani API.
Timbre 3 introduces expressions in your speech in the form of audio tags. You write a short cue where the delivery should change, and the voice performs it. There are 12 of them, covering laughter, breath, vocal style and pacing, across 11 Indian languages and many voices.
We built it for the places voice already does real work:
→ Voice agents and IVR that soften when they apologize and slow down when they read out an amount
→ The voice layer inside apps, from learning lessons to game characters
→ Creator productions, where the acting now lives in the script
Under the tags, Timbre 3 reads numbers and dates the way people say them, with natural prosody across every voice.
What would you make it say first?
#VoiceAI #TextToSpeech #Timbre #TTS
[Launch Series : Day 2/10] Most KYC checks sit in a queue before anyone even looks at them.
On Plexus, an agent reads the PAN card the moment it comes in, pulls out the details, and calls the customer to confirm them directly, no manual entry, no back-and-forth over email.
The verification that used to sit in a queue now happens in one continuous flow: document in, call placed, confirmation done.
Automate every workflow with Plexus.
Join the waitlist: gnani.ai/plexus-early-access
hashtag#AgenticAI hashtag#VoiceAI hashtag#ConversationalAI hashtag#Automation hashtag#Gnani hashtag#AIAgents hashtag#KYC