Generate
Convert text to natural-sounding speech with AI voices
Generate lets you turn any text into lifelike audio using AI voices. Choose from a variety of voices, enter your text, and download the audio file.
How to Generate Speech
Choose a voice from the dropdown. Voices are grouped by language. Click the play button to preview how each voice sounds.
Type or paste the text you want to convert. Character limits depend on the voice type (see table below).
Click Generate or press Cmd+Enter (Mac) / Ctrl+Enter (Windows). Wait for processing to complete.
Preview the audio in the player, then click Download to save the file.
Voice Types
The catalog has 57 public text-to-speech voices across four voice families.
| Voice Type | Character Limit | Output Formats | Special Features |
|---|---|---|---|
| Gemini 3.8 voices | 1,000 characters | WAV | Style instructions plus inline vocal tags like <sigh> and <short pause>; includes Spanish voices for Spain and Mexico |
| Gemini 3.1 voices | 1,000 characters | WAV | Style instructions plus inline expression tags like [whispering] and [pause] |
| Gemini 2.5 voices | 1,000 characters | WAV | Style instructions for tone/emotion |
| Grok voices | 1,000 characters | MP3, WAV | Multi-language support with expressive tags |
Gemini voices show a text box where you can describe how you want the voice to sound (e.g., "warm and friendly" or "serious and professional"). The same voice name, such as kore or zephyr, is available on Gemini 2.5, 3.1, and 3.8, so pick the model version you prefer.
Grok voices support both MP3 and WAV output. They also support expressive tags like [laugh], [sigh], [pause], and wrapper tags like <whisper>...</whisper>, <soft>...</soft> for fine-grained control over delivery.
Emotion Tags (Gemini 3.8 voices)
Gemini 3.8 voices accept inline vocal tags in any transcript language. Keep the tags in English.
<argh>, <breath>, <heavy breath>, <exhales>, <cackle>, <cheer>, <chuckle>, <chuckles>, <cough>, <cry>, <gasp>, <giggle>, <groan>, <growl>, <grunt>, <grr>, <hiss>, <laugh>, <laughter>, <moan>, <pant>, <pff>, <phew>, <scream>, <shout>, <shriek>, <sigh>, <sighs>, <sneeze>, <snicker>, <snort>, <sob>, <throat-clearing>, <tsk>, <whimper>, <whispers>, <whispering>, <yawn>, <short pause>, <long pause>
Example: Ven aquí. <short pause> <laughter> No me lo puedo creer.
Credits
Credits are calculated based on text length and voice type:
- Gemini voices: ~1 credit per token (based on text and audio length)
- Grok voices: 4 credits per 100 characters
You need at least 10 credits to generate audio. Your remaining credits are shown at the top of the page.