Introduction
Gemini 3.8 Flash TTS API is the expressive speech option for acted dialogue and long narration: 70 voices, line-level direction and WAV delivery, with support for over 130 languages. Build Flash scenes with text for a solo reading or speakers and dialogue for up to two performers across 20 turns. Each turn supplies speaker, text and optional style, with a matching speaker name; text and each turn allow 10,000 characters. Speaker settings can override accent, style, pace and profile, while an omitted voice_id selects Kore.
| Field | Value |
|---|---|
| Input | Text |
| Output | Audio |
| Required field | text / dialogue (10,000) |
| Optional fields | Choose voices with |
| Result | Flash renders one editable WAV track in 24 kHz, 16-bit mono PCM, ready for mixing or encoding. |
| Longest clip | 16,384 audio tokens |
| Billed quantity | Flash TTS reserves 660 seconds of audio while generation runs; settlement uses the returned file’s measured duration and releases the unused reservation. |
| Retention | Identify Flash output as synthetic speech, secure rights to the script, and download the WAV before its 14-day retention expires. |
Request parameters
| Parameter | Required | Description |
|---|---|---|
text | No | Keep the Flash transcript within 10,000 characters and use , or for local vocal events; separate character turns belong in dialogue. at least 1 characters · at most 10000 characters |
dialogue | No | Build Flash scenes with text for a solo reading or speakers and dialogue for up to two performers across 20 turns. at least 1 items · at most 20 items |
speakers | No | Build Flash scenes with text for a solo reading or speakers and dialogue for up to two performers across 20 turns. at least 1 items · at most 2 items |
voice_id | No | Cast a Flash TTS narrator from 70 voices, including Fola, Neno, Charon and Algieba, with Kore used by default. |
style | No | Set style for the sustained acting of a Flash reading; an empty value keeps the voice’s delivery, and dialogue speakers may supply their own style. |
pace | No | Shape Flash narration with natural, |
accent | No | Use accent to direct the English pronunciation of a Flash performance; leaving it out keeps the selected voice’s accent, and dialogue speakers inherit it only when they supply n… |
instructions | No | For expressive Flash performances, put sustained direction in instructions and reserve , or for moments inside the transcript. at most 1000 characters |
scene | No | For expressive Flash performances, put sustained direction in instructions and reserve , or for moments inside the transcript. at most 500 characters |
filler_words | No | Flash dialogue can add conversational |
temperature | No | For alternate Flash takes, temperature accepts 0 to 2, with higher settings allowing more variation; omission uses the model default without changing the rate per audio second. |
Pricing
$0.00032 / second
Flash TTS reserves 660 seconds of audio while generation runs; settlement uses the returned file’s measured duration and releases the unused reservation.
Use cases
Audiobooks and long-form narration
Use Flash’s expressive delivery for chapters with difficult pronunciations or changing emotions, auditioning the chosen narrator across passages before assembling the book.
Character and companion voices
Give each scripted character a Flash voice and direct the sustained emotion through style, keeping the actual words in the transcript.
Uncensored audio stories
In SpicyAPI’s Flash TTS tests, the model read the submitted monologues and narration in full and performed the bracketed cues; audition new scripts because a cue may still be spoken aloud.
Voice tracks for video
Export the Flash WAV as the spoken track for an avatar or lip-sync workflow; its measured duration determines the amount of speech the video must accommodate.
Prompt guide & pro tips
Dialogue and voices
Build Flash scenes with text for a solo reading or speakers and dialogue for up to two performers across 20 turns. Each turn supplies speaker, text and optional style, with a matching speaker name; text and each turn allow 10,000 characters. Speaker settings can override accent, style, pace and profile, while an omitted
voice_idselects Kore.Delivery control
For expressive Flash performances, put sustained direction in instructions and reserve , or for moments inside the transcript. The controls style, accent, pace and scene are combined into delivery notes; a dialogue line’s style takes precedence over its speaker’s style. A solo script stays a one-speaker performance, and each take needs listening for pronunciation or accidentally spoken directions.
Billing
Flash TTS reserves 660 seconds of audio while generation runs; settlement uses the returned file’s measured duration and releases the unused reservation.
Gemini 3.8 Flash TTS API is the expressive speech option for acted dialogue and long narration: 70 voices, line-level direction and WAV delivery, with support for over 130 languages.
For expressive Flash performances, put sustained direction in instructions and reserve , or for moments inside the transcript. The controls style, accent, pace and scene are combined into delivery notes; a dialogue line’s style takes precedence over its speaker’s style. A solo script stays a one-speaker performance, and each take needs listening for pronunciation or accidentally spoken directions.
Build Flash scenes with text for a solo reading or speakers and dialogue for up to two performers across 20 turns. Each turn supplies speaker, text and optional style, with a matching speaker name; text and each turn allow 10,000 characters. Speaker settings can override accent, style, pace and profile, while an omitted voice_id selects Kore.
Flash dialogue can add conversational filler_words between two speakers; this starts disabled and does not affect solo narration.
Flash TTS exposes request-scoped cloning through a dialogue speaker’s reference_audio_url and consent_audio_url, without voice_id. Supply two WAV recordings of the same consenting adult, made with the same microphone in the same room, each no larger than 10 MB: 10–30 seconds of natural target-language speech for the reference and the required permission statement for consent. Synthetic recordings are ineligible, and no persistent voice ID is created; SpicyAPI has not yet validated this path with voice-owner recordings.
For Flash TTS scripts, SpicyAPI adds no content filter, but a successful reading does not confer script, recording or voice rights. Obtain those rights and comply with the applicable licenses and terms before publishing a performance.
Flash TTS reserves 660 seconds of audio while generation runs; settlement uses the returned file’s measured duration and releases the unused reservation.
For the Flash TTS consent recording, speak the required statement: “I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.”
For Flash TTS scripts, SpicyAPI adds no content filter, but a successful reading does not confer script, recording or voice rights. Obtain those rights and comply with the applicable licenses and terms before publishing a performance.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "google/gemini-3.8-flash-tts/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"voice_id": "Kore"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.













