Voice Infra, made in India
Voice Infra that Indian builders need.
Natural conversations. In your language. Voice agents and speech models, built and run in India.
Have an access code? Build, test, and explore.
Why Voice InfraGo on. Say नमस्ते.
Why builders need Voice Infra
A typical builder stitches together six or seven products for one voice agent.
Voice Infra brings every layer into one system.
- The line. Theirs: Twilio / Plivo / Exotel, vendor edge, often outside India — network 1 · a separate telephony integration. Ours: Indian carrier trunks, our own interconnect, no CPaaS in between.
- The gateway. Theirs: the same CPaaS — the gateway is theirs, vendor region — still network 1 · nothing here is yours to tune. Ours: our SIP gateway, same rack as the worker.
- Orchestration. Theirs: Pipecat Cloud / LiveKit / Vapi, US region — network 2 · a TLS handshake and a vendor queue. Ours: our worker, a LAN hop, one data centre.
- Noise. Theirs: Krisp, vendor cloud — network 3 · the audio leaves again. Ours: Mira denoise, in process, no network at all.
- ASR. Theirs: Deepgram / AssemblyAI / Sarvam, US or Indian region, per vendor — network 4 · a separate speech recognition stream. Ours: Mira ASR, the same card as the model and the voice.
- LLM. Theirs: OpenAI / Anthropic / Gemini, US region — network 5 · another connection for every reply. Ours: open source LLM, the same card.
- TTS. Theirs: ElevenLabs / Cartesia, US region — network 6 · a separate speech synthesis stream. Ours: Mira TTS, the same card, first audio back on the same LAN.
Response time
Stitched stackVoice Infra
- ASR + VAD + buffer900 ms690 ms
- LLM400 ms150 ms
- TTS300 ms110 ms
Now, let’s talk about the most important aspect: price.
India needs pricing made for India.
One rupee used to buy you
a call from an STD box.
One rupee. A voice agent.Now the machine on the line talks back.
Stack
Five products to connect.
One conversation to get right.
Every layer. One Mira Stack.
₹1* for voice AI / min
नमस्ते, मैं आशु बोल रहा हूं। आपकी EMI पांच तारीख को due है — क्या online pay करेंगे?
Rendered by Mira TTS · 2026-09-03
*₹1/min for voice AI on T1. ₹1.50/min end to end with telephony and insights. Commercial terms are being finalised.
-
We started by renting GPU capacity and building our fleet in Indian data centres. Then we took charge of how that compute runs, scales and serves every call.
Rented compute. Operated by us. -
TTS is the most compute-intensive and expensive layer. We trained Mira TTS from scratch and wrote its inference engine to deliver 3× the throughput of the industry standard.
24 streams per GPU, compared with the industry’s 8. -
Before opening to the public, we spent three months running live with beta customers. Real calls, real feedback. Test, fix, test again.
Three months with beta customers before public access. -
Bootstrapping gives us room to focus on the core: better models, faster inference and lower costs. We build for customers, on our own terms.
Customer revenue goes back into the core.
Building with Voice Infra.
Real conversations. In production.
Meet some of the teams building with miraiminds.
- bik.ai
- servall
- bot.space
- 11za
- iLeads
- We Win
- Credresolve
- inTalk
Built for builders
All this infrastructure. One API call.
The GPU fleet, the speech models, the inference engine and all the orchestration. We bring it together and keep it running. You build the conversation.
Python
from mirai import Mirai
# Uses MIRAI_API_KEY
mirai = Mirai()
call = mirai.calls.create(
agent_id="YOUR_AGENT_ID",
to="+91XXXXXXXXXX",
)cURL
curl https://api.voice.miraiminds.co/v2/calls \
-H "Authorization: Bearer $MIRAI_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: YOUR_UNIQUE_CALL_ID" \
-d '{
"agent_id": "YOUR_AGENT_ID",
"to": "+91XXXXXXXXXX"
}'Use an agent you’ve configured in your workspace, and the number you want to call.
FAQs
Before you build.
Does it really cost ₹1?
Yes. ₹1 per minute on T1 is for an actual voice agent: ASR, LLM, TTS and orchestration. Telephony and insights are separate: ₹0.30 (30 paise) and ₹0.20 (20 paise) per minute. With both included, an end-to-end call costs ₹1.50 per minute. Commercial terms and volume commitments are being finalised. Please contact us to discuss your use case.
How fast does it reply?
The response breakdown above is 950 ms, including 150 ms for the LLM and 110 ms for TTS. The rest covers ASR, VAD and buffering. Actual response time varies with speech, network conditions and load.
Which languages?
Hindi, English, Hinglish and Gujarati are live today. Bengali, Marathi, Telugu, Tamil and Kannada follow. Each language ships when it clears evaluation, and the date is announced then.
Where does the audio go?
Voice processing runs in Indian data centres. You can review call recordings, transcripts and costs in the console. Website analytics and booking providers are covered separately in our privacy notice.
Do I need my own telephony?
No. On T1, our telephony adds ₹0.30 per minute to the ₹1 voice AI rate. Insights add another ₹0.20, making ₹1.50 per minute end to end. You can also bring your own trunks. Commercial terms are being finalised.
Can you support a larger deployment?
Yes. Talk to us about call volume, concurrency, workflows and the languages you need. We’ll work through capacity and commercial terms with you before you commit.
How do I try it?
Open the sandbox at sandbox.voice.miraiminds.co to build and test an agent. You can also start a conversation with the demo at the top of this page to hear Voice Infra in your browser.
Is there an API?
Yes — a v2 REST API with one auth header: create an agent, place a call, read the transcript, recording and cost. Mira TTS also speaks OpenAI’s /v1/audio/speech. Everything is documented at docs.miraiminds.co.
Still have a question? Talk to us. We’re the people building it. sneh@miraiminds.co