All models
Voice & realtimeLive
GoogleGemini 3.8 Flash TTS
Google's speech-generation model for expressive narration, character voices and dialogue in 130 languages.
Plain-English overview
What Gemini 3.8 Flash TTS actually is
Turn a written script into spoken audio, choosing a voice and directing how each line sounds. Flash TTS is the creative option in this pair, aimed at narration, accents and character performances.
Both models support custom voice design and two-speaker scripts. They generate speech, not answers: a conversational assistant still needs separate listening and reasoning components. They do not use the Gemini Live API.
Good fit for
- Audiobooks
- Character dialogue
- Multilingual narration
Category comparison
The facts that matter for voice models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Price basis
- $0.50 text input · $9 audio output / 1M tokensToken-, character-, or minute-based price for the listed access route.
- Interaction mode
- Text-to-speech with two-speaker dialogueSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior.
- Published latency
- Not publishedProvider-published measurement with its stated exclusions; not a Cody test.
- Languages
- 130 languagesProvider-documented language coverage or a clear unpublished marker.
- Tools & control
- Voice design and replication; no function callingNative function calling, reasoning, or speech-control features.
- Context or input limit
- 8,192 input · 16,384 output tokensDocumented token or character limit where it is meaningful.
API and provider access
Where to get Gemini 3.8 Flash TTS
Availability
Regions and access stage
Available through the Gemini API and Google AI Studio in supported regions.
AI Studio voice replication excludes Illinois, Texas, the EEA, UK, Switzerland and India. This restriction is not a blanket ban on TTS in those regions.
Check live availabilityData and training
The route matters.
Google says paid Gemini API prompts and responses are not used to improve its products. Unpaid-service content generally may be used, with different treatment for EEA, UK, and Swiss users; check the current terms for your account and region.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Gemini 3.8 Flash TTS FAQ
What is Gemini 3.8 Flash TTS?
Google's speech-generation model for expressive narration, character voices and dialogue in 130 languages. Turn a written script into spoken audio, choosing a voice and directing how each line sounds. Flash TTS is the creative option in this pair, aimed at narration, accents and character performances.
When was Gemini 3.8 Flash TTS released?
Gemini 3.8 Flash TTS was released on September 23, 2026 according to the cited provider materials.
Where can I access Gemini 3.8 Flash TTS?
Available through the Gemini API and Google AI Studio in supported regions. The access routes listed in this guide are Google.
How much does Gemini 3.8 Flash TTS cost?
$0.50 text input · $9 audio output / 1M tokens. Introductory Standard rates through December 31, 2026; both rates double on January 1, 2027. Audio uses 25 tokens per second. Caching and other service tiers have different rates.
Where is Gemini 3.8 Flash TTS available?
Available through the Gemini API and Google AI Studio in supported regions. AI Studio voice replication excludes Illinois, Texas, the EEA, UK, Switzerland and India. This restriction is not a blanket ban on TTS in those regions.
Is my Gemini 3.8 Flash TTS API data used for training?
Google says paid Gemini API prompts and responses are not used to improve its products. Unpaid-service content generally may be used, with different treatment for EEA, UK, and Swiss users; check the current terms for your account and region. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Head-to-head comparisons
Gemini 3.8 Flash TTS vs Gemini 3.8 Flash-Lite TTS
Google's lower-cost speech-generation model for read-aloud features and high-volume audio in 101 languages.
Open full comparisonGemini 3.8 Flash TTS vs Eleven v3 Conversational
ElevenLabs' expressive realtime text-to-speech model for natural dialogue, emotional delivery, audio tags, and more than 70 languages.
Open full comparisonGemini 3.8 Flash TTS vs Inworld Realtime TTS-2
Inworld's newest expressive realtime text-to-speech model, designed to remember conversational delivery and speak in more than 100 languages.
Open full comparison
