Gemini 3.8 Flash-Lite TTS API

About Gemini 3.8 Flash-Lite TTS

Google's Gemini 3.8 Flash-Lite TTS, released in September 2026, is the faster, lower-cost sibling of 3.8 Flash TTS: send a script, pick one of 30 voices and get back a WAV file, usually within seconds.

Call it with the model name google/gemini-3.8-flash-lite-tts/text-to-speech on POST /jobs/createTask, from 0.03 credits per second ($0.0003). New accounts get 30 free credits to try it in the Playground first.

Introduction

Gemini 3.8 Flash Lite TTS is the faster sibling of Gemini 3.8 Flash TTS: the same 30 prebuilt voices, the same request fields and the same output, a single WAV file at 24 kHz, 16-bit, mono PCM. In our tests the median task finished generating in about 7 seconds. Send text with up to 5,000 characters and a voice_id (default Kore); add style, accent, pace, instructions and scene to shape the reading, or send dialogue and speakers for two voices in one clip.

Key features

Quick turnaround

A 270-character paragraph came back as 22 to 26 seconds of audio, and the median task finished in about 7 seconds. That suits drafts, previews and pipelines that read many short lines.

The same controls as Flash

style, accent and pace set the manner, English accent and rhythm; instructions and scene describe how and where the words are spoken and are not read aloud; temperature (0–2) sets how much takes vary.

Two voices in one clip

speakers holds one or two entries with a name, a voice_id and optional accent, style, pace and profile. Each dialogue line is {speaker, text}, up to 20 lines of 250 characters each.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Drafting voiceovers

Check timing and wording of a script with a quick read before producing the final take.

Many short lines

Interface prompts, notifications, flashcards and other short reads where turnaround matters more than a performed delivery.

Simple two-voice exchanges

Scripted Q&A or tutorial dialogue where two clear voices are enough.

Prompt guide & pro tips

Spell sounds out instead of bracketing them

Bracketed cues such as [sighs] are not reliably performed on Lite: in our tests the model sometimes read the word inside the brackets aloud. Write the sound instead ("Mmm…", "ahh…"), or use Gemini 3.8 Flash TTS when performed cues matter.

Let punctuation carry the delivery

Commas and ellipses slow the reading down; short sentences make it more conversational.

The voice keeps its character in any language

Pick the voice for its character; it does not change with the language of the script.

API quick start

Call the Gemini 3.8 Flash-Lite TTS API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model google/gemini-3.8-flash-lite-tts/text-to-speech and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "google/gemini-3.8-flash-lite-tts/text-to-speech",
  "input": {
    "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
    "voice_id": "Kore"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Gemini 3.8 Flash-Lite TTS API questions

All Gemini models

Gemini 3.8 Flash TTS reliably acts out bracketed cues like [whispering] and gives the more expressive read. Flash Lite is the cheaper choice for volume.

• Gemini 3.8 Flash TTS APIExpressive speech that acts out cues like [laughing]From 0.05 credits per second
• Gemini 3.8 Flash-Lite TTS APIFast, lightweight speech in 30 voicesFrom 0.03 credits per second
• Gemini 2.5 Pro TTS APIDirectable voices for narration and two-person dialogueFrom 0.07 credits per second

Other audio APIs

• MiniMax Speech 2.8 HD APIHigh-fidelity speech in 400+ voices with emotion controlFrom 18 credits per 1,000 characters
• Grok TTS API71 voices across 20 languages with speech tagsFrom 3 credits per 1,000 characters
• Seed Speech 2.0 API41 voices with tone set in plain languageFrom 11 credits per 1,000 characters
• MiniMax Speech 2.8 Turbo APIFast speech in 400+ voices with emotion controlFrom 11 credits per 1,000 characters
• Qwen3 TTS APIOpen-source speech with tone and pace set in plain wordsFrom 11 credits per 1,000 characters
• Chatterbox APIEnglish speech that can match a short voice sampleFrom 6 credits per run

More about Gemini 3.8 Flash-Lite TTS

Try it

Gemini 3.8 Flash-Lite TTS AI Voice Generator onlineCreate audio with Gemini 3.8 Flash-Lite TTS in PopNow

Docs

Gemini 3.8 Flash-Lite TTS model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesWebhooks: get Gemini 3.8 Flash-Lite TTS results without polling