Skip to main content
Core.Today
|
GoogleFastHigh

Gemini 3.1 Flash TTS

Google Gemini 3.1 Flash native-audio TTS via Replicate. Style instructions (separate from the spoken text) plus 30 preset voices and 40+ language/locale codes, with inline markup tags for expressive delivery ([sigh], [whispering], [shouting], etc.).

299 credits
per 1000 characters (input text + generated speech)
Native-audio TTS powered by Gemini 3.1 Flash
Separate style-instruction field (prompt) independent from the spoken text
30 preset voices
40+ language/locale codes (BCP-47), including Korean, Japanese, Spanish, French, German, and more
Inline markup tags ([sigh], [laughing], [whispering], [shouting], [extremely fast]) for expressive delivery

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "google/gemini-3.1-flash-tts",
  "input": {
    "prompt": "Say this in a calm, professional tone, like a documentary narrator.",
    "text": "์˜ค๋Š˜ ์†Œ๊ฐœํ•  ์ œํ’ˆ์€ ์ตœ์‹  ๋ฌด์„  ์ด์–ดํฐ์ž…๋‹ˆ๋‹ค. ๋›ฐ์–ด๋‚œ ์Œ์งˆ๊ณผ ํŽธ์•ˆํ•œ ์ฐฉ์šฉ๊ฐ์„ ๋™์‹œ์— ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.",
    "voice": "Kore",
    "language_code": "ko-KR"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringNoSay the following.Style instructions to control how the text is spoken. Use natural language to describe the desired tone, pace, accent, and emotion. For example: 'Say this in a calm, professional tone' or 'Speak with excitement and energy'. Maximum 4,000 bytes.
textstringYes-The text to convert to speech. Supports markup tags like [sigh], [laughing], [whispering], [shouting], [extremely fast] for expressive delivery. Maximum 4,000 bytes.
voicestringNoKoreVoice to use for speech generation
AchernarAchirdAlgenibAlgiebaAlnilamAoedeAutonoeCallirrhoeCharonDespinaEnceladusErinomeFenrirGacruxIapetusKoreLaomedeiaLedaOrusPulcherrimaPuckRasalgethiSadachbiaSadaltagerSchedarSulafatUmbrielVindemiatrixZephyrZubenelgenubi
language_codestringNoen-USLanguage for the speech output
af-ZAam-ETar-001ar-EGaz-AZbe-BYbg-BGbn-BDca-ESceb-PHcmn-CNcmn-twcs-CZda-DKde-DEel-GRen-AUen-GBen-INen-USes-419es-ESes-MXet-EEeu-ESfa-IRfi-FIfil-PHfr-CAfr-FRgl-ESgu-INhe-ILhi-INhr-HRht-HThu-HUhy-AMid-IDis-ISit-ITja-JPjv-JVka-GEkn-INko-KRkok-INla-VAlb-LUlo-LAlt-LTlv-LVmai-INmg-MGmk-MKml-INmn-MNmr-INms-MYmy-MMnb-NOne-NPnl-NLnn-NOor-INpa-INpl-PLps-AFpt-BRpt-PTro-ROru-RUsd-INsi-LKsk-SKsl-SIsq-ALsr-RSsv-SEsw-KEta-INte-INth-THtr-TRuk-UAur-PKvi-VN

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Korean narration with style direction

Narrates Korean text in a calm, professional tone using the Kore voice.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "google/gemini-3.1-flash-tts",
  "input": {
    "prompt": "Say this in a calm, professional tone, like a documentary narrator.",
    "text": "์˜ค๋Š˜ ์†Œ๊ฐœํ•  ์ œํ’ˆ์€ ์ตœ์‹  ๋ฌด์„  ์ด์–ดํฐ์ž…๋‹ˆ๋‹ค. ๋›ฐ์–ด๋‚œ ์Œ์งˆ๊ณผ ํŽธ์•ˆํ•œ ์ฐฉ์šฉ๊ฐ์„ ๋™์‹œ์— ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.",
    "voice": "Kore",
    "language_code": "ko-KR"
  }
}'

Expressive English delivery with markup tags

Uses inline markup tags for an excited, expressive delivery in English.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "google/gemini-3.1-flash-tts",
  "input": {
    "prompt": "Speak with excitement and energy, like announcing a big surprise.",
    "text": "[laughing] You won't believe this offer โ€” it's fifty percent off, today only! [extremely fast] Don't miss out!",
    "voice": "Puck",
    "language_code": "en-US"
  }
}'

Tips & Best Practices

1Use `prompt` for tone/pace/emotion direction and `text` for the actual words to speak โ€” they're separate fields
2Wrap markup tags like [whispering], [sigh], [shouting] directly inside `text` for expressive delivery, not in `prompt`
3Set language_code to match the language of `text` (e.g. ko-KR for Korean) for accurate pronunciation
4Keep both prompt and text under 4,000 bytes each

Use Cases

Multilingual narration and voiceover for video content
Expressive character voices using markup tags and style instructions
Localized audio for apps/products across 40+ languages
Rapid prototyping of script read-throughs before final production