Text to Speech for Indian Languages

Before any audio is generated, the input text goes through a normalization stage that expands abbreviations, formats numbers, and resolves ambiguities. In English, this is relatively straightforward. In Indian languages, it gets complicated fast. Consider a sentence like "Dr. Sharma ka appointment 18 Jan ko 7:30 AM pe hai." The system needs to know that "Dr." should be spoken as "Doctor" (not "D-R"), that "18 Jan" becomes "athaarah January," that "7:30 AM" becomes "saadhe saat baje subah," and that "Sharma" is a proper noun that should be pronounced naturally.

Sarvam's normalizer handles Indian names, addresses (including PIN codes and landmark references), currency amounts in rupees, phone numbers in the Indian 10-digit format, and mixed-script text where Devanagari and Latin characters appear in the same sentence. This preprocessing step is what makes the difference between robotic output and speech that sounds like a real person reading the text aloud.

Prosody (rhythm, stress, intonation) is what makes a question sound like a question and separates natural speech from robotic speech. Hindi prosody is fundamentally different from English: stress is more evenly distributed across syllables, and the pitch contour of a Hindi sentence follows a different arc than its English translation. When an English-trained TTS model generates Hindi, it applies English stress patterns to Hindi words. The result is technically intelligible but sounds wrong to native speakers.

Bulbul V3 uses an LLM-based text analysis layer to infer emphasis, pauses, and pacing before any audio is generated. Each of the 11 supported languages gets its own prosodic representation: Hindi narration follows the rising-falling pattern of North Indian speech, while Tamil output uses the syllable-timed rhythm of Dravidian languages. This per-language modeling is a big part of why Sarvam scored highest in the Josh Talks blind evaluation. 20,000+ votes from 500+ annotators across 11 languages, and Bulbul V3 came out ahead of ElevenLabs and Cartesia.

An estimated 350 million Indians speak English as a second language, and the vast majority of them mix it freely with their primary language. A customer support agent might say "Aapka order dispatch ho gaya hai, expected delivery by tomorrow evening." A teacher might explain "Friction ka coefficient zyada matlab zyada resistance, simple." This is not broken grammar. It is normal Indian communication, and any TTS system that cannot handle it will produce jarring, unnatural output every time a language boundary appears.

Sarvam handles code-switching at the model level, not through a pipeline that detects language boundaries and routes them to separate engines. When Bulbul V3 hits a Hinglish sentence, it generates audio in a single pass. No pauses at the language boundary, no voice quality shift, no accent change. Same for Tanglish, Benglish, Marathi-English, and other mixes. This matters most for voice agents and IVR systems, where callers switch languages mid-sentence and any glitch is immediately noticeable.

There are 35+ voices across all 11 languages, recorded from professional voice artists at up to 48 kHz. They are organized by use case (Edtech, Customer Support, Advertising, Storytelling, Social Media) rather than dumped into a flat list. Arjun works well for authoritative banking communications. Meera suits warm customer service. Ritu brings energy to storytelling. You can also adjust pace (0.5x to 2x), pitch, and emotional expressiveness via API parameters. If you need a branded voice, Sarvam offers consent-based voice cloning: provide a 30-60 second speech sample, give explicit consent, and the system creates a custom voice. Browse the full catalog at dashboard.sarvam.ai.

Voice agents are replacing traditional call center recordings with dynamic, context-aware speech. A banking voice agent can read back a customer's account balance in Hinglish ("Aapka EMI payment of rupees 12,345 due hai by 15th March") without pre-recording any of those specific sentences. In BFSI deployments, Bulbul V3 handles loan collection calls with financial terminology (EMI, credit records, late charges) across Hindi, Kannada, and other languages. Healthcare voice agents confirm appointments with complex medical terms like "Comprehensive Thyroid Profile with Anti-TPO Antibodies test" without mispronouncing them. Sarvam's sub-250ms streaming latency means callers hear responses without awkward pauses.

IVR systems use TTS to generate dynamic menu prompts that change based on context. Instead of maintaining thousands of pre-recorded audio files for every possible menu option in every language, telecom and banking companies generate prompts on the fly. A single API call creates "Aapka current balance hai rupees 12,345. PIN change karne ke liye 1 dabayein" in natural Hindi.

Voice notifications deliver OTP codes, appointment reminders, delivery updates, and payment confirmations as spoken calls. For the hundreds of millions of Indian users who are more comfortable with voice than text, spoken notifications have significantly higher engagement than SMS. TTS makes it possible to personalize every call without recording each message individually.

YouTube creators in India are using TTS to produce videos faster. Educational channels, news aggregators, and storytelling accounts generate Hindi, Tamil, or Telugu narration from scripts without needing a recording studio. A creator who publishes daily can write a script and have broadcast-ready audio in seconds.

Podcast production becomes accessible to anyone with a script. Writers, journalists, and educators can turn articles into audio episodes in any Indian language. The AI voices are natural enough for extended listening, which matters for podcast formats where listeners spend 20-40 minutes with a single voice.

Audiobook creation at scale is now feasible for Indian language publishers. Recording a full audiobook traditionally takes weeks and costs lakhs. With TTS, a 300-page book can be converted to audio in hours. Sarvam's expressive voices with emotion control produce audiobooks that listeners actually enjoy, not the flat robotic output that gave early TTS audiobooks a bad reputation.

Voiceover for explainer videos, product demos, corporate presentations, and documentary narration can be generated in 11 languages from a single script. Production teams that previously needed separate voice artists for each language can now localize content in minutes.

Dubbing and localization teams use TTS to create first-draft voiceovers for video content that needs to reach multiple Indian language audiences. A marketing video produced in English can be localized to Hindi, Tamil, and Telugu in minutes. Professional dubbing studios use TTS as a reference track; content teams with smaller budgets use it as the final output.

E-learning platforms use TTS to narrate courses in regional languages. India's National Education Policy emphasizes mother-tongue instruction, and TTS makes it economically viable to offer the same course in 11 languages without recording 11 separate voiceover tracks. Students retain more information when they learn in their first language.

Corporate training content reaches a wider workforce when narrated in regional languages. A compliance training module for a bank with branches across India can be generated in Hindi, Marathi, Tamil, and Bengali from a single script. Updates to policies or procedures are reflected instantly without re-recording.

Presentations with embedded narration are more engaging than slide decks alone. Sales teams, trainers, and educators add TTS narration to their slides so the content can be consumed asynchronously without a live presenter.

Advertising teams produce radio spots, digital audio ads, and video ad voiceovers at scale. A national campaign that needs to run in 8 languages can generate all the audio variants from a single script, test different voices and tones, and iterate in hours instead of weeks.

Accessibility is one of the most important applications of text to speech. For visually impaired users, TTS enables access to websites, documents, and digital services. For users with reading difficulties, it provides an alternative way to consume written content. India has over 60 million people with visual impairments and hundreds of millions who are more comfortable with spoken information than written text. Sarvam TTS supports screen reader integration and can narrate content in the user's preferred Indian language at adjustable speeds.

Sign up at sarvam.ai/try/tts-api to get your API key. Install the Python SDK with pip install sarvamai or the Node.js SDK with npm install sarvamai. Both SDKs use an OpenAI-compatible interface, so if you have integrated any LLM API before, the pattern will feel familiar. Your first TTS generation takes under 5 minutes from signup to working audio.