Sonna
Overview

Text to Speech

AI text-to-speech: turn text into natural AI voiceovers with ElevenLabs, Google Cloud, and Gemini voices in 60+ languages.

Sonna's Text to Speech (TTS) studio lets you convert scripts, articles, and book chapters into high-quality spoken audio using natural-sounding AI voices.


Supported Narration Models

We integrate top-tier speech synthesis engines to provide a range of languages, latency profiles, and accents:

ProviderModel NameCredit Cost (per 1K chars)Max Script LengthKey Features
ElevenLabsEleven v32,100 / 1K chars5,000 charsMaximum expression and emotional range.
ElevenLabsMultilingual v22,100 / 1K chars10,000 charsExceptional translation pronunciation in 29+ languages.
ElevenLabsFlash v2.51,050 / 1K chars40,000 charsUltra-fast generation, ideal for long scripts.
Google CloudNeural2500 / 1K chars3,000 charsStandard narration, clean and clear.
Google CloudWavenet500 / 1K chars3,000 charsBalanced narration quality.
Gemini2.5 Flash700 / 1K chars3,000 charsFast, conversational speech tone.
Gemini2.5 Pro1,050 / 1K chars3,000 charsContext-aware, natural emphasis.

Rates are shown per 1,000 characters for readability, but billing is per character (pro-rated). A 500-character script on Eleven v3 costs 1,050 credits, not 2,100. Minimum charge is 1 character.


Character Limits & Free Tier Restrictions

To protect backend resources, character limits per request are restricted based on your subscription plan:

  • Free Plan Users: Constrained to a maximum of 1,000 characters per request, regardless of the model chosen.
  • Pro & Max Plan Users: Can generate up to the maximum character limits listed in the model table above (e.g., up to 40,000 characters using Flash v2.5).

Voice Library

Browse Sonna's curated library of ready-to-use voices, filterable by language, accent, gender, and optimal use case (e.g. narrator, storytelling, energetic, professional). The library spans all three providers:

  • ElevenLabs — the most expressive voices, including premium professional voices.
  • Google Cloud — Neural2 and WaveNet, clean and reliable across many languages.
  • Gemini — natural, conversational multilingual voices.

Pick a voice from the dropdown in the Text to Speech studio, then choose a model that fits (see the table above). Save the ones you use most to your favorites.

On this page