Gemini TTS: Voices, Languages & Prompting Guide
·
Gemini TTS is the neural engine behind Audiobook Maker's PREMIUM voices. This guide covers the available voices, supported languages, and how to steer delivery with prompts.
Voice options
30 distinct voices, each with its own character. The voice name is fixed; the descriptor summarises its natural tone.
| Voice | Character |
|---|---|
| Zephyr | Bright |
| Puck | Upbeat |
| Charon | Informative |
| Kore | Firm |
| Fenrir | Excitable |
| Leda | Youthful |
| Orus | Firm |
| Aoede | Breezy |
| Callirrhoe | Easy-going |
| Autonoe | Bright |
| Enceladus | Breathy |
| Iapetus | Clear |
| Umbriel | Easy-going |
| Algieba | Smooth |
| Despina | Smooth |
| Erinome | Clear |
| Algenib | Gravelly |
| Rasalgethi | Informative |
| Laomedeia | Upbeat |
| Achernar | Soft |
| Alnilam | Firm |
| Schedar | Even |
| Gacrux | Mature |
| Pulcherrima | Forward |
| Achird | Friendly |
| Zubenelgenubi | Casual |
| Vindemiatrix | Gentle |
| Sadachbia | Lively |
| Sadaltager | Knowledgeable |
| Sulafat | Warm |
Supported languages
Gemini TTS supports the following languages (BCP-47 code in parentheses):
Arabic (ar), Filipino (fil), Bangla (bn), Finnish (fi), Dutch (nl), Galician (gl), English (en), Georgian (ka), French (fr), Greek (el), German (de), Gujarati (gu), Hindi (hi), Haitian Creole (ht), Indonesian (id), Hebrew (he), Italian (it), Hungarian (hu), Japanese (ja), Icelandic (is), Korean (ko), Javanese (jv), Marathi (mr), Kannada (kn), Polish (pl), Konkani (kok), Portuguese (pt), Romanian (ro), Russian (ru), Spanish (es), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Vietnamese (vi), Afrikaans (af), Albanian (sq), Amharic (am), Armenian (hy), Azerbaijani (az), Basque (eu), Belarusian (be), Bulgarian (bg), Burmese (my), Catalan (ca), Cebuano (ceb), Chinese Mandarin (cmn), Croatian (hr), Czech (cs), Danish (da), Estonian (et), Latvian (lv), Lithuanian (lt), Luxembourgish (lb), Macedonian (mk), Maithili (mai), Malagasy (mg), Malay (ms), Malayalam (ml), Mongolian (mn), Nepali (ne), Norwegian Bokmål (nb), Norwegian Nynorsk (nn), Odia (or), Pashto (ps), Persian (fa), Punjabi (pa), Serbian (sr), Sindhi (sd), Sinhala (si), Slovak (sk), Slovenian (sl), Swahili (sw), Swedish (sv), Urdu (ur).
Prompting guide
The model infers delivery from the transcript automatically. You can steer it further with inline tags and structured directions.
Inline audio tags
Inline modifiers such as [whispers], [laughs], [excitedly], [bored] and [shouting] change tone, pace and emotional quality. Be creative and experiment with delivery variations.
Advanced prompting elements
- Audio Profile — character name and role definition.
- Scene — environmental context that sets mood and physical setting.
- Director’s Notes — performance guidance: style, pacing, accent.
- Sample Context — contextual grounding for a natural entry into the performance.
- Transcript — the exact spoken words, paired with audio tags.
Key guidance
Don't feel you have to describe everything — giving the model space to fill the gaps often helps naturalness. Balance specificity with creative freedom, and prefer industry terminology and layered characteristics over plain emotional labels.
How to use prompts in Audiobook Maker
Audiobook Maker narrates the chapter text directly, so you add prompt cues inside the text itself, in one of two ways:
- Edit the input TXT file before uploading, inserting tags/cues directly in the text.
- Or download the generated .ABM file, edit the chapter texts, and re-upload the modified .ABM to Audiobook Maker.
Source: Google AI — Speech generation
Try Audiobook Maker Free →