Guide · Speech APIs
Hindi text-to-speech APIs compared: prices and features, October 2026.
Two Hindi text-to-speech APIs price in rupees: our Fourier TTS at ₹1.80 per 1,000 characters, and Sarvam's Bulbul from ₹2.00 on pay as you go, less on its monthly plans. ElevenLabs, Google, Azure, Amazon Polly, OpenAI and Cartesia price in US dollars. Here is every published price as of 16 October 2026, each with its source, and a way to test the voices on your own lines.
What does each Hindi TTS API cost?
Published list prices, read on 16 October 2026 from the page in the last column, in each vendor’s currency, without volume deals. “Hindi, as published” is the vendor’s own description.
| Provider and model | Published price | Hindi, as published | Streaming | Source |
|---|---|---|---|---|
| Frequency, Fourier TTS | ₹1.80 per 1,000 characters (pay as you go and Business) | Hindi, English, Gujarati, Tamil, Telugu and Hinglish; voices that code-switch into English | HTTP PCM stream; WebSocket | Quickstart |
| Sarvam, Bulbul V4 Flash | ₹2.00 per 1,000 characters pay as you go; ₹1.85 Pro; ₹1.70 Growth and Business | Hindi, English, “enhi” code-mixed voices and other Indian languages | REST, HTTP streaming, WebSocket | Pricing, models |
| Sarvam, Bulbul V3 | ₹3.00 per 1,000 characters pay as you go; ₹2.70 Growth and Business | 11 languages, 10 Indian plus English | REST, HTTP streaming, WebSocket | Pricing |
| ElevenLabs, Eleven v4 Turbo; Flash/Turbo | $0.04 per 1K characters | Hindi listed for v4 Turbo (90+ languages) and Flash v2.5 | v4 Turbo over a WebSocket | Pricing, models |
| ElevenLabs, Eleven v4; v3; Multilingual v2 | $0.08 per 1K characters | Hindi listed for each | Pricing | |
| Google Cloud, Chirp 3: HD | US$30 per 1M characters; first 1M a month free | 30 hi-IN voices | Bidirectional streaming | Pricing, voices |
| Google Cloud, Neural2; WaveNet and Standard | US$16; US$4 per 1M characters | 4 Neural2, 6 WaveNet and 6 Standard hi-IN voices | Pricing | |
| Microsoft Azure, Neural; Neural HD | $15; $22 per 1M characters | hi-IN neural voices and MAI-Voice HD voices | Speech SDK and REST | Pricing, languages |
| Amazon Polly, Neural; Standard | $16.00; $4.00 per 1M characters | Kajal (Neural) and Aditi (Standard), bilingual Hindi and Indian English | Audio stream per request | Pricing, voices |
| OpenAI, tts-1; tts-1-hd | $15.00; $30.00 per 1M characters | Follows Whisper’s language list, which includes Hindi; voices “optimized for English” | Chunked transfer encoding | Pricing, guide |
| OpenAI, gpt-4o-mini-tts | $0.60 per 1M text input tokens; $12.00 per 1M audio output tokens | As above | As above | Pricing |
| Cartesia, Sonic 3.6 | Credit plans from free (20K credits a month) to $299 (8M); 1 credit is 1 character | Hindi among 44 languages; expanded support for Hindi in Latin script | Bytes, SSE and WebSocket | Pricing, model |
Google counts every character you send, spaces, newlines and SSML tags included. We report what we billed in X-Chars-Billed, and a request that fails or stops halfway is free.
What do 10 lakh characters cost?
Ten lakh (1,000,000) characters is a fair month for a small app. At list price, before tax and free tiers:
| Provider and model | Working | Cost |
|---|---|---|
| Fourier TTS | 1,000 × ₹1.80 | ₹1,800 |
| Sarvam Bulbul V4 Flash, pay as you go | 1,000 × ₹2.00 | ₹2,000 |
| Sarvam Bulbul V3, pay as you go | 1,000 × ₹3.00 | ₹3,000 |
| ElevenLabs v4 Turbo | 1,000 × $0.04 | $40 |
| ElevenLabs v4 | 1,000 × $0.08 | $80 |
| Google Chirp 3: HD | 1 × US$30 (the first 1M each month is free) | US$30 |
| Azure Neural | 1 × $15 | $15 |
| Amazon Polly Neural | 1 × $16.00 | $16.00 |
| OpenAI tts-1 | 1 × $15.00 | $15.00 |
| Cartesia Startup plan | 1.25M credits included | $49 a month |
Convert dollars at your own rate. At low volume, Google’s and Amazon’s free tiers can bring the bill to zero. GST is extra on ours.
Which voice do listeners prefer?
Voice Arena plays two voices reading the same line and asks people to pick one, blind, then turns the votes into Bradley-Terry Elo ratings. On its Hindi board, pulled on 16 October 2026 across all categories, Fourier TTS, our own voice, scored 993 ± 25 from 440 votes and ranked 11th of 19. Sarvam’s Bulbul V3 scored 959 ± 9 from 3,882 votes and ranked 14th.
Fourier TTS leads Bulbul V3 in general conversation, 1053 to 961, and in content creation and education, 1014 to 901. Bulbul V3 leads in customer support, 984 to 971, and in media and entertainment, 967 to 956. Mira has far fewer votes, so its range is wider, and Bulbul V4 Flash wasn’t on that snapshot.
Ten models ranked above Fourier TTS, led by ElevenLabs’ new Eleven v4, with Google’s Gemini TTS models, Cartesia’s Sonic-3.6 and ElevenLabs’ Eleven v3 among them. OpenAI’s gpt-4o-mini-tts and Azure’s Dragon HD Omni ranked below, and Amazon Polly isn’t on the board. Votes keep arriving, so check the live leaderboard.
How do I test Hindi TTS on my own script?
A leaderboard averages other people’s sentences. Test yours:
- Take the twenty or thirty lines your app says most.
- Add names, rupee amounts, dates, phone numbers, an OTP, and English words like “order”, “refund” or “delivery”.
- Write Hindi in Devanagari with English in Latin script, and also in Roman script if that’s how your text arrives.
- Render every line in each shortlisted voice, labelled with model and voice.
- Play them, shuffled and unlabelled, to people who speak Hindi daily. Ask what sounded wrong, not only which they liked.
- Play the best two over a real phone call at 8 kHz, which hides some errors and exposes others.
For a live agent, also time the gap before the reply’s first audio. The Hindi TTS guide has starter sentences, and the OpenAI-compatible TTS guide gets you audio in a few lines.
Pricing a whole calling agent instead? Ours cost ₹1 a minute on the volume plan, voice included.
Sources
These are the references this guide is built on.
References reviewed on . Measurement dates and experimental limits are stated in the article. Check current API and runtime documentation when integrating.
- docs.miraiminds.co
- Fourier TTS quickstart and billing
- sarvam.ai
- Sarvam API pricing
- docs.sarvam.ai
- Sarvam Bulbul models
- elevenlabs.io
- ElevenLabs API pricing
- elevenlabs.io
- ElevenLabs models and languages
- cloud.google.com
- Google Cloud Text-to-Speech pricing
- cloud.google.com
- Google supported voices and languages
- cloud.google.com
- Google Chirp 3: HD voices
- azure.microsoft.com
- Azure Speech pricing
- learn.microsoft.com
- Azure Speech language support
- aws.amazon.com
- Amazon Polly pricing
- docs.aws.amazon.com
- Amazon Polly bilingual voices
- developers.openai.com
- OpenAI API pricing
- developers.openai.com
- OpenAI text-to-speech guide
- cartesia.ai
- Cartesia pricing
- docs.cartesia.ai
- Cartesia Sonic 3.6
- voicearena.com
- Voice Arena Hindi TTS leaderboard
Questions
These are the questions developers ask us most.
Which Hindi TTS API is cheapest?
It depends on your volume and your currency. In rupees, Fourier TTS is ₹1.80 per 1,000 characters on pay as you go. Sarvam's Bulbul V4 Flash is ₹2.00 on pay as you go, and ₹1.70 on its Growth and Business plans, which carry a monthly payment. Google's and Amazon's free tiers cover the first million or more characters a month. Convert the dollar prices at your own rate.
Which Hindi TTS voice sounds best?
It depends on the script. On Voice Arena's Hindi leaderboard, pulled on 16 October 2026, Fourier TTS ranked 11th of 19 models and Sarvam's Bulbul V3 14th. Bulbul V3 led Fourier TTS in customer support and in media and entertainment. Test your shortlist on your own lines, with native speakers.
Which Hindi TTS APIs handle Hinglish?
Each vendor describes it differently. Fourier TTS voices switch into English. Sarvam's Bulbul V4 Flash has voices tagged enhi for English-Hindi code-mixing. Amazon Polly's Aditi and Kajal switch between Hindi and Indian English within a sentence. Cartesia says Sonic 3.6 has expanded support for Hindi written in Latin script. Test your own mixed sentences either way.
Is Fourier TTS ₹1 a minute?
No. ₹1 a minute is the price of a whole phone agent on our volume plan. Fourier TTS on its own is ₹1.80 per 1,000 characters, before GST.
Still deciding? Ask us.
Fifteen minutes with the team that builds it. Bring your script, or your hardest call.
Book 15 minutes