Gemini 2.5 Pro TTS, Text to Speech, Input
Gemini 2.5 Pro TTS: lifelike speech from text.
A tradução deste card ainda não está disponível; parte do conteúdo aparece em inglês.
Gemini 2.5 Pro TTS converts text into high-quality, expressive speech. It supports multiple languages and voice tones, making it ideal for content creators who need professional voiceovers without recording studios.
Use it for narrations, audiobooks, voice assistants, or dynamic audio content. The model captures nuances like emphasis and pacing, delivering speech that sounds human and engaging.
What sets it apart is its ability to handle complex text, including punctuation and formatting, to produce clear and natural output with minimal artifacts.
- Video voiceovers
- Podcast narration
- Audiobook production
- Accessibility audio
- Interactive voice responses
Delivers speech with appropriate emotion and emphasis.
Works with many languages and accents seamlessly.
Produces audio quickly, even for long texts.
- Use punctuation like commas and periods to control pacing.
- Specify desired voice style (e.g., 'cheerful', 'serious') in the prompt.
- Keep paragraphs short for more natural phrasing.
- Test different voices to match your content's tone.
- May struggle with highly technical jargon or unusual names.
- Very long texts might require chunking for best quality.
- Voice cloning or custom voice creation is not supported.
Produce a deep, resonant voice for a movie trailer: 'In a world where nothing is as it seems, one hero must rise. This summer, prepare for the unexpected.'
Narrate this children's story with a playful, friendly voice: 'Once upon a time, in a land of candy clouds and chocolate rivers, lived a little bunny named Pip.'
Generate a professional, clear voice for a business presentation: 'Our quarterly results show a 20% growth in revenue, driven by innovative product launches and customer satisfaction.'
A number that ensures the same input produces the same audio output.
Limits the pool of possible speech patterns; lower values make output more predictable.
Sets the target length of the audio in seconds.
Controls randomness in voice inflection; lower values produce steadier speech.
Adjusts how closely the output follows the prompt; higher values mean stricter adherence.
Os preços exibidos são o que você paga na Muitto. Sem surpresas.
Can I use my own voice?
No, the model offers preset voices but does not support custom voice cloning.
How long can the audio be?
There is no strict limit, but very long texts may need to be split into segments.
Does it support multiple languages?
Yes, it supports many languages and regional accents.