Google Gemini 3.8 Flash TTS
Press play and hear Google Gemini 3.8 Flash TTS. Then choose the voice that fits.
Hello! This is how my voice sounds. I will read your text clearly and naturally.
What your project costs
The sample line above costs about $0.0014.
Estimate per minute of speech. Final cost uses actual audio tokens and input text.
Estimate for speech duration. The final charge uses input text and output audio tokens.
Same line, two voices
Two voices are easier to judge side by side. Pick a pair and hear them back to back.
A runs 5.4 s, B runs 5.6 s.
What it's the best tool for
- 30 preset voices with samples
- Written delivery instructions
- Supported dialogue workflow
- MP3 and WAV
When to reach for something else
- Up to 10,000 characters per form request
- Listen through names and numbers
- Page samples use preset voices
Four scenarios where it pays for itself
More about Google Gemini 3.8 Flash TTS
Gemini 3.8 Flash TTS: expressive narration and dialogue
Gemini 3.8 Flash TTS is Google’s model for reading prepared text aloud. NetRoom provides 30 preset voices with real Russian and English samples. Use it for narration, character lines and dialogue when voice choice and delivery matter for the material.
Available in NetRoom
Describe delivery in a separate instruction, or assign voices to characters in the supported dialogue workflow. MP3 and WAV output are available, with up to 10,000 characters per request in the form. The voice-wall samples were synthesised by this model rather than substituted with actor recordings.
Preparing the result
Audition several voices using the same phrase. Submit a short part of your own text and describe the intended delivery. Use punctuation for pauses and write numbers as they should be spoken. For longer material, review names and transitions between sections.
Practical uses
- Audio story: Choose a voice and narrative delivery.
- Dialogue: Assign character voices in the supported workflow.
- Audio guide: Read self-contained sections of a tour.
- Video narration: Prepare speech for later editing.
Reviewing the result
Up to 10,000 characters per form request; Listen through names and numbers; Page samples use preset voices.
What changed Google Gemini 3.8 Flash TTS
Use Google Gemini 3.8 Flash TTS via the API
The same engine, straight from your code: one key and one balance for text, images, video and sound. Pay only for the requests you make.
curl https://netroom.ai/api/v1/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "google/gemini-38-flash-tts", "input": {"text": "Hello! This is how my voice sounds.", "voice": "Kore", "output_format": "MP3"}}'
The model id is already in the example. The full parameter reference and prices live in GET /api/v1/models and in the docs.
Pick a voice.
Paste your text.
Samples are free to listen to. You pay only for what you generate.