Cualify.
OutboundInboundBookingCollectionsPricingSecurityBlog
Sign inStart a pilot

Cualify Field Notes

Building India's AI calling stack — in public.

One short essay every other Friday on voice AI, Indian SMB GTM, and what we ship. No spam. Unsubscribe in one click.

Cualify.

AI calling agency for Indian SMBs. Multilingual voice agents, INR billing, DPDP-ready from day one.

Built in Mumbai · Stored in Mumbai

Product

  • Outbound sales
  • Inbound support
  • Appointment booking
  • Collections
  • Voice library
  • Docs

Company

  • Pricing
  • Cualify vs Bolna
  • Changelog
  • Security
  • Blog
  • About
  • Contact

Legal

  • Terms of service
  • Privacy policy
  • Data Processing
  • Acceptable Use
  • 15-day refund

Compliance

  • DPDP Act 2023
  • TRAI / DLT
  • 99.5% SLA
  • Sub-processors
  • Customer KYC
  • Contact DPO

© 2026 Cualify Technologies. All rights reserved.

[email protected]·[email protected]·+91 80 0000 0000

Field Notes·Voice tech·4 April 2026·3 min read

Indic voice quality teardown: Sarvam, Smallest, ElevenLabs

Eight evaluators, three providers, six languages, one blind test. Latency, naturalness, accent fidelity.

By Utsav Rana

Voice quality is the single biggest reason an AI calling pilot dies. A human picks up, hears something off — robotic, wrong accent, weird cadence — and hangs up before the disclosure even finishes. We ran a structured blind test of the three TTS providers we use in production. Here's what we learned.

Test setup

  • Three providers: Sarvam AI, Smallest AI, ElevenLabs.
  • Six languages: Hindi, Tamil, Telugu, Marathi, Bengali, English (Indian).
  • Eight evaluators across India — native speakers of each language.
  • 12 sample utterances per language: greeting, intent capture, objection handling, closing.
  • Each utterance synthesized by all three providers, presented blind in randomised order.
  • Evaluators rated naturalness (1-5), accent fidelity (1-5), and would-they-stay-on-the-call (yes/no).

Naturalness scores (5-point scale, higher is better)

Hindi

  • Sarvam: 4.4 — clearly the strongest. Indian accent baseline, no English-accented Hindi.
  • Smallest: 3.8 — clean output, occasional slight English-accented inflection.
  • ElevenLabs: 3.2 — usable but evaluators flagged 'this is an Indian voice trained on English data'.

Tamil

  • Sarvam: 4.6 — best in class. Native cadence, dialect-aware.
  • Smallest: 3.4 — passable, some pronunciation drift on retroflexes.
  • ElevenLabs: 2.8 — evaluators said 'sounds like Hindi-speaker reading Tamil'.

English (Indian)

  • Sarvam: 4.0 — solid Indian English, slight monotone on long utterances.
  • Smallest: 4.2 — best-in-class for Indian English specifically.
  • ElevenLabs: 4.5 — best overall for English; the 'Olivia' and 'Ethan' voices we use on the Premium tier are ElevenLabs-powered.

Latency (TTS-only, p50, ms to first audio)

  • Sarvam: 280ms
  • Smallest: 220ms (best)
  • ElevenLabs: 380ms

Anything under 400ms is conversational; the human ear doesn't notice. All three pass the bar. Where it matters: full agent-loop latency (STT + LLM + TTS) — we'll cover that in a follow-up post.

Stay-on-the-call rate

The most consequential number. Across 96 evaluations:

  • Sarvam (Indic only): 91% would stay on the call.
  • Smallest (Indic only): 76% would stay.
  • ElevenLabs (Indic only): 58% would stay.
  • ElevenLabs (English only): 88% would stay.

What we ship

Cualify uses Sarvam for all six Indic languages, ElevenLabs for English-only voices on the Scale tier (where the brand often wants a more polished American/British alternative). The decision was painfully obvious from the data.

What surprised us

Three things:

  1. 01The Bengali results were closer than we expected — Sarvam still won, but Smallest's Bengali was within 0.3 points. Bengali might be a place where alternatives become viable.
  2. 02Tamil was the language where the gap was widest — and where Cualify customers are most demanding. If you're targeting Tamil-speaking SMBs, you cannot afford a non-Sarvam TTS.
  3. 03Punjabi (which we tested on the side, n=4) was rough across all three. We're holding off on shipping Punjabi voices until either Sarvam or a new entrant raises the bar.

Methodology caveats

Three caveats worth flagging:

  • Evaluators were Cualify-network volunteers, not paid. Selection bias toward urban/tech-adjacent listeners.
  • We didn't test against a baseline of human voice agents in the same pipeline. That's a follow-up.
  • The TTS landscape moves fast — these scores are from March 2026. Smallest in particular is improving rapidly. Re-test in 6 months.

Want the raw evaluator scores? Email [email protected] and I'll send the spreadsheet. We're publishing this stuff because the Indian AI voice ecosystem is too small for vendors to fight blind.

Read more

  • Compliance

    DPDP Act 2023 — what an AI calling team actually has to do

  • Benchmark

    Human vs AI: cost per qualified lead, the real Indian numbers

Got a question about this post? Email us →