MCP / Models / Voice, music and sound
Gemini 3.8 Flash-Lite TTS MCP: low-cost speech at volume
Google Gemini 3.8 Flash-Lite TTS turns text into fast, low-cost speech with 30 voices and style control, built for high volume, in over 100 languages. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Gemini 3.8 Flash-Lite TTS in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/gemini-3-8-flash-lite-tts.md. Help me connect the FlyMy.AI MCP to this assistant, then run Gemini 3.8 Flash-Lite TTS (flymyai/gemini-3_8-flash-lite-tts) for this task: Read this paragraph aloud with Gemini 3.8 Flash-Lite TTS in a calm, friendly voice and send me the audio file.
What Gemini 3.8 Flash-Lite TTS does
The lowest-cost of Google's two Gemini 3.8 speech models, made for high volume, voice-agent pipelines, read-aloud features and everyday single-voice speech. It takes the same inputs as Gemini 3.8 Flash TTS: text (up to 5,000 characters, with sound tags), voice (30 built-in voices, Kore by default), style, and speakers for a two-speaker dialogue. It finds the language from the text, and Google lists over 100. The result is one WAV file (24 kHz, mono, 16-bit). For heavy acting, many characters or hard pronunciations use Gemini 3.8 Flash TTS. Billing counts the tokens of the text and of the speech, and Google doubles its speech prices on 1 January 2027. It does not clone voices, take audio in or translate.
Gemini 3.8 Flash-Lite TTS inputs
Every input of flymyai/gemini-3_8-flash-lite-tts as its live schema lists them. Returns audio (array).
| Input | Type, values and default |
|---|---|
# text | string required The words to speak, read exactly as written: up to 5,000 characters, about 5 minutes of speech. Short sounds go in as tags such as <laugh>, <sigh> or <short pause>; directions go in style, not here. With speakers, write one line for each turn as Name: words. Billed by the speech made, a minute of it (about 1,000 characters of English) at $0.0135 until 2026-12-31 and $0.027 from 2027-01-01 on Flash, $0.009 and $0.018 on Flash-Lite |
# voice | string optional Allowed: Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callirrhoe, Autonoe, Enceladus, Iapetus, Umbriel, Algieba, Despina, Erinome, Algenib, Rasalgethi, Laomedeia, Achernar, Alnilam, Schedar, Gacrux, Pulcherrima, Achird, Zubenelgenubi, Vindemiatrix, Sadachbia, Sadaltager, Sulafat Default: Kore The voice, 30 to pick from; Kore (firm) by default. Zephyr bright, Puck upbeat, Charon informative, Kore firm, Fenrir excitable, Leda youthful, Orus firm, Aoede breezy, Callirrhoe easy-going, Autonoe bright, Enceladus breathy, Iapetus clear, Umbriel easy-going, Algieba smooth, Despina smooth, Erinome clear, Algenib gravelly, Rasalgethi informative, Laomedeia upbeat, Achernar soft, Alnilam firm, Schedar even, Gacrux mature, Pulcherrima forward, Achird friendly, Zubenelgenubi casual, Vindemiatrix gentle, Sadachbia lively, Sadaltager knowledgeable, Sulafat warm. The language is read from the text. Not used with speakers |
# style | string optional How to say the text, in plain words: cheerful and friendly, whispering, speaking slowly, out of breath. Up to 500 characters; leave it empty for Google's own delivery. It sets delivery only: pick a voice for age, gender or accent. With speakers it applies to every turn |
# speakers | string optional Optional dialogue of two speakers: a JSON object of two names and their voices, such as {"Joe": "Puck", "Jane": "Kore"}. text is then a script with each turn starting its line as Joe: words (a line without a name goes on with the turn before it), and voice is not used |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/gemini-3_8-flash-lite-ttsflymyai/gemini-3_8-flash-lite-ttsflymyai/gemini-3_8-flash-lite-ttsGemini 3.8 Flash-Lite TTS price
$0.50 per 1M text tokens and $6.00 per 1M audio tokens; speech is 25 audio tokens per second, so about $0.009 per minute of speech plus the text; one request costs at most $0.10107. A run at the default settings costs $0.009. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call Gemini 3.8 Flash-Lite TTS from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/gemini-3_8-flash-lite-tts",
"input": {
"text": "Welcome to FlyMy.AI."
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash-lite-tts/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash-lite-tts/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'text=Welcome to FlyMy.AI.'Questions about Gemini 3.8 Flash-Lite TTS
Do I need a Google API key for Gemini 3.8 Flash-Lite TTS?
No. Gemini 3.8 Flash-Lite TTS runs on FlyMy.AI's account, so you need no Google key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Gemini 3.8 Flash-Lite TTS cost?
$0.50 per 1M text tokens and $6.00 per 1M audio tokens; speech is 25 audio tokens per second, so about $0.009 per minute of speech plus the text; one request costs at most $0.10107. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use Gemini 3.8 Flash-Lite TTS in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Read this paragraph aloud with Gemini 3.8 Flash-Lite TTS in a calm, friendly voice and send me the audio file." Your agent reads the inputs with get_model_schema and runs flymyai/gemini-3_8-flash-lite-tts with run_model.
What does Gemini 3.8 Flash-Lite TTS need as input?
Gemini 3.8 Flash-Lite TTS requires text; it also takes 3 optional inputs, each listed on this page with its allowed values and default.
Can I call Gemini 3.8 Flash-Lite TTS from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash-lite-tts/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





