Text to speech

Romani text to speech

Romani narration, education and customer messages, with natural AI voices from $5 per million characters, the same price in every language.

Get your API key · See pricing

Text to speech: what you pay

Published pay-as-you-go text-to-speech prices
ProviderMode or modelUSD per 1M characters
GiggyFast$5.00
GiggyStreaming$10.00
Fish AudioS2.1 Pro$15.00
InworldRealtime TTS-2 Flash$15.00
OpenAItts-1$15.00
AzureNeural TTS$15.00
InworldRealtime TTS-2$25.00
AmazonPolly Generative$30.00
DeepgramAura-2$30.00
GoogleChirp 3: HD$30.00
OpenAItts-1-hd$30.00
CartesiaSonic-3.6 · Scale overage$38.00
ElevenLabsFlash v2.5$40.00
ElevenLabsMultilingual v2 / v3 / v4$80.00
MiniMaxSpeech-02-HD$100.00

ElevenLabs, OpenAI, Deepgram, Google, Amazon and Azure checked November 11, 2026; Fish and Inworld October 20; Cartesia and MiniMax October 13.

Hear Romani voices

Browse every Romani voice in the Voice Library

Generate Romani speech in three steps

  • Enter your Romani text

    Type or paste your Romani script. Add expression tags such as [whisper] or [short pause] to guide the delivery.

  • Choose a Romani voice

    Pick a Romani voice from the Voice Library or create your own, then choose Batch, Fast or Streaming.

  • Download or call the API

    Download 24 kHz MP3 audio from the app, or request the same voice from the Speech API in your product.

Built for a wide range of uses

  • Voice agents

    Give Romani assistants and support agents a natural voice with Streaming audio.

  • Podcasts and audiobooks

    Narrate Romani chapters and episodes with a voice listeners can stay with.

  • Video voiceovers

    Voice Romani explainers, ads and social videos without a recording booth.

  • E-learning

    Turn Romani lessons and training into clear, consistent narration.

  • Games and characters

    Give Romani characters distinct voices, with emotion and non-verbal tags.

  • Accessibility

    Read Romani articles, documents and interfaces aloud.

One price in every language

Giggy counts Unicode code points in the full input text, including spaces and punctuation, at the same rate in all 240+ supported languages. Credits are prepaid with no subscription and shared across text to speech, speech to text and voice creation.

Shape the delivery

Add expression tags such as [whisper], [excited] or [short pause] to your Romani script. Giggy supports 50+ emotions, 20+ delivery styles and 40+ non-verbal events, plus speaking-speed control.

Build Romani speech into your product

Send Romani text to /v1/text-to-speech with a voice ID and your API key, or use the OpenAI-compatible speech endpoint or the Giggy MCP server. Batch and Fast return MP3; Streaming returns progressive 24 kHz PCM.

Read the API docs · API reference

Frequently asked questions

What is Romani text to speech?

Text to speech turns written Romani text into natural-sounding audio. Giggy generates Romani speech in the app or through the API with voices made for Romani.

How much does Romani text to speech cost?

Giggy Fast costs $5 and Streaming main0 per 1,000,000 characters with Pro, Studio or Scale credits, the same as every other language. Batch is free within request and queue limits.

Where can I hear Romani voices?

Listen to the top Romani voices on this page or browse every Romani voice in the Voice Library, with samples, accents and suggested uses.

Can I create a custom Romani voice?

Yes. Voice Design creates a new Romani voice from a written description for 1,000 credits. Voice Clone reference audio supports a separate set of languages, listed on the voice cloning page.

Can I use Romani voices through an API?

Yes. Every library voice has a voice ID for the Giggy Speech API, its OpenAI-compatible speech endpoint and the Giggy MCP server.