Post-Cutoff
Search For AI agents

Google DeepMindGemini 3 familyCurrentSpeech and audioReleased 22 Sep 2026

Gemini 3.8 Flash-Lite TTS

The cheaper Gemini 3.8 text-to-speech model.

Model idgemini-3.8-flash-lite-tts

Price$0.50 in, $6 out per 1M tokens

Checked25 October 2026

Where it stands

17newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

Before it from Google
Gemini 3.8 Live15 Sep 2026
Weights
Closed weights; access is hosted only.

How to call it

2 ways to use Gemini 3.8 Flash-Lite TTS, with the model id each provider expects.

Providers, model ids, endpoints and docs for Gemini 3.8 Flash-Lite TTS
ProviderModel idEndpointDocs
Gemini API gemini-3.8-flash-lite-tts https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash-lite-tts:generateContent ai.google.dev
Google AI Studio aistudio.google.com

Pricing

Prices for Gemini 3.8 Flash-Lite TTS
Input$0.50 per 1M tokens
Output$6 per 1M tokens
Batch input$0.25
Batch output$3

As published: “USD per 1M tokens (text in / audio out); introductory through 2026-12-31, then $1.00 / $12.00 (batch $0.50 / $6.00) from 2027-01-01; free tier available”.

Source: ai.google.dev, checked 25 October 2026.

Specs

Input
Text
Output
Audio
Context window
8,192 tokens
Max output
16,384 tokens
Open weights
No
Licence
Proprietary
Released
22 September 2026
Status
Current
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Low-cost everyday TTS in 101 languages

    Built to replace gemini-3.1-flash-tts-preview for everyday single-speaker generation; 101 languages; audio out at $6 per 1M tokens vs $9 for Gemini 3.8 Flash TTS (intro prices).

    Source: ai.google.dev

  • Voice design and stored voice replication

    Custom Voice design personas, prebuilt voices plus the Extended Voice Library, and persistent stored replicated voices (optional stateless keys).

    Source: ai.google.dev

  • Hume VoiceEQ 0.914

    Found after launch

    Scored 0.914 on Hume’s blind Real-World VoiceEQ leaderboard, just behind Gemini 3.8 Flash TTS (0.920) and ahead of Cartesia Sonic 3.6 (0.840).

    Source: hume.ai

Notes

Artificial Analysis TTS arena (https://artificialanalysis.ai/text-to-speech/leaderboard), read 2026-10-25: rank #8, Elo 1252, listed at $11.0 per 1M characters (AA’s normalisation; Google bills per 1M tokens). GA 2026-09-22 with gemini-3.8-flash-tts (per the Gemini API changelog, see entry). Supports Batch API, Flex and Priority inference; no Live API, function calling, thinking or caching. Default unary output WAV (audio/wav). Multi-speaker dialogue is recommended on the Flash TTS model instead. Model page last updated 2026-10-09; it does not label the model GA or preview. Output SynthID-watermarked (per Google’s 3.8 TTS launch). Sibling: gemini-3-8-flash-tts.

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash-lite-tts:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Say warmly: Welcome back!"}]}],
       "generationConfig":{"responseModalities":["AUDIO"]}}'

Sources: model page, pricing, launch blog, AA leaderboard.