Introduction
Gemini 3.8 Flash-Lite TTS targets production read-aloud and voice-agent cascades; SpicyAPI exposes 70 preset voices, per-line direction and scripts up to 10,000 characters.
| Field | Value |
|---|---|
| Input | Text |
| Output | Audio |
| Required field | text / dialogue (10,000) |
| Optional fields |
|
| Result | One WAV file, 24 kHz, 16-bit, mono |
| Longest clip | 16,384 audio tokens |
| Billed quantity | Gemini 3.8 Flash-Lite TTS is billed by measured audio seconds; the running task holds 660 seconds of balance and releases the unused amount after measurement, while failed requests are not charged. |
| Retention | Generated audio is kept for 14 days |
Request parameters
| Parameter | Required | Description |
|---|---|---|
text | No | For a Gemini 3.8 Flash-Lite TTS take, place only the spoken script in text, up to 10,000 characters, and keep delivery direction in instructions. at least 1 characters · at most 10000 characters |
dialogue | No | For Gemini 3.8 Flash-Lite TTS dialogue, match each line’s speaker to a name in speakers: one or two speakers, at most 20 lines and 10,000 characters per line, returned together… at least 1 items · at most 20 items |
speakers | No | For Gemini 3.8 Flash-Lite TTS dialogue, match each line’s speaker to a name in speakers: one or two speakers, at most 20 lines and 10,000 characters per line, returned together… at least 1 items · at most 2 items |
voice_id | No | The Gemini 3.8 Flash-Lite TTS preset library exposes 70 voices with Kore as the default; assign |
style | No | Set style for the overall performance of your chosen Gemini 3.8 Flash-Lite TTS voice; a dialogue speaker’s own style takes precedence over this shared direction. |
pace | No | For Gemini 3.8 Flash-Lite TTS, pace offers natural, |
accent | No | Choose an English accent for the 70-voice Gemini 3.8 Flash-Lite TTS library with accent; in dialogue this supplies the fallback for speakers without their own accent. |
instructions | No | Direct Gemini 3.8 Flash-Lite TTS with instructions for mood and delivery, using style, accent, pace and scene where needed; listen to a preview because generative speech may int… at most 1000 characters |
scene | No | Direct Gemini 3.8 Flash-Lite TTS with instructions for mood and delivery, using style, accent, pace and scene where needed; listen to a preview because generative speech may int… at most 500 characters |
filler_words | No | Gemini 3.8 Flash-Lite TTS can add filler words to two-speaker dialogue when |
temperature | No | For repeat Gemini 3.8 Flash-Lite TTS recordings, temperature ranges from 0 to 2 and higher values increase delivery variation; omit it for the model default without changing the… |
Pricing
$0.00021 / second
Gemini 3.8 Flash-Lite TTS is billed by measured audio seconds; the running task holds 660 seconds of balance and releases the unused amount after measurement, while failed requests are not charged.
Use cases
High-volume narration
Product copy, lesson scripts, article read-outs and batches of short lines where turnaround and cost matter more than acting nuance.
Character and companion voices
Give a chat character a voice of its own and answer in seconds. Short, spoken-style sentences and careful punctuation carry most of the tone.
Uncensored audio stories
In SpicyAPI tests, Gemini 3.8 Flash-Lite TTS read the submitted adult scripts without omissions; that observation is not a guarantee, and you remain responsible for recording rights, informed consent and lawful publication without impersonation.
Voice tracks for video
Export the Gemini 3.8 Flash-Lite TTS WAV as the voice track for an avatar or lip-sync step, checking its measured duration before setting the video timeline.
Prompt guide & pro tips
Dialogue and voices
For Gemini 3.8 Flash-Lite TTS dialogue, match each line’s speaker to a name in speakers: one or two speakers, at most 20 lines and 10,000 characters per line, returned together in one WAV.
Delivery control
Direct Gemini 3.8 Flash-Lite TTS with instructions for mood and delivery, using style, accent, pace and scene where needed; listen to a preview because generative speech may interpret a cue differently.
Billing
Gemini 3.8 Flash-Lite TTS is billed by measured audio seconds; the running task holds 660 seconds of balance and releases the unused amount after measurement, while failed requests are not charged.
Gemini 3.8 Flash-Lite TTS targets production read-aloud and voice-agent cascades; SpicyAPI exposes 70 preset voices, per-line direction and scripts up to 10,000 characters.
High-volume narration
Product copy, lesson scripts, article read-outs and batches of short lines where turnaround and cost matter more than acting nuance.
Character and companion voices
Give a chat character a voice of its own and answer in seconds. Short, spoken-style sentences and careful punctuation carry most of the tone.
Uncensored audio stories
In SpicyAPI tests, Gemini 3.8 Flash-Lite TTS read the submitted adult scripts without omissions; that observation is not a guarantee, and you remain responsible for recording rights, informed consent and lawful publication without impersonation.
Voice tracks for video
Export the Gemini 3.8 Flash-Lite TTS WAV as the voice track for an avatar or lip-sync step, checking its measured duration before setting the video timeline.
For Gemini 3.8 Flash-Lite TTS dialogue, match each line’s speaker to a name in speakers: one or two speakers, at most 20 lines and 10,000 characters per line, returned together in one WAV.
In SpicyAPI tests, Gemini 3.8 Flash-Lite TTS read the submitted adult scripts without omissions; that observation is not a guarantee, and you remain responsible for recording rights, informed consent and lawful publication without impersonation.
accent
Choose an English accent for the 70-voice Gemini 3.8 Flash-Lite TTS library with accent; in dialogue this supplies the fallback for speakers without their own accent.
dialogue
For Gemini 3.8 Flash-Lite TTS dialogue, match each line’s speaker to a name in speakers: one or two speakers, at most 20 lines and 10,000 characters per line, returned together in one WAV.
instructions
Direct Gemini 3.8 Flash-Lite TTS with instructions for mood and delivery, using style, accent, pace and scene where needed; listen to a preview because generative speech may interpret a cue differently.
pace
For Gemini 3.8 Flash-Lite TTS, pace offers natural, rapid_fire, the_drift and staccato; slower readings use more billable seconds even when the 10,000-character script stays the same.
scene
Direct Gemini 3.8 Flash-Lite TTS with instructions for mood and delivery, using style, accent, pace and scene where needed; listen to a preview because generative speech may interpret a cue differently.
speakers
For Gemini 3.8 Flash-Lite TTS dialogue, match each line’s speaker to a name in speakers: one or two speakers, at most 20 lines and 10,000 characters per line, returned together in one WAV. On SpicyAPI, Gemini 3.8 Flash-Lite TTS temporary cloning requires dialogue and an adult owner’s reference_audio_url plus consent_audio_url, without voice_id: WAV files up to 10 MB each, a 10–30-second natural reference, the same microphone and room, and the prescribed spoken consent; AI recordings are excluded and owner-supplied recordings have not yet verified this path.
style
Set style for the overall performance of your chosen Gemini 3.8 Flash-Lite TTS voice; a dialogue speaker’s own style takes precedence over this shared direction.
temperature
For repeat Gemini 3.8 Flash-Lite TTS recordings, temperature ranges from 0 to 2 and higher values increase delivery variation; omit it for the model default without changing the per-second rate.
text
For a Gemini 3.8 Flash-Lite TTS take, place only the spoken script in text, up to 10,000 characters, and keep delivery direction in instructions.
voice_id
The Gemini 3.8 Flash-Lite TTS preset library exposes 70 voices with Kore as the default; assign voice_id separately for each named dialogue speaker.
filler_words
Gemini 3.8 Flash-Lite TTS can add filler words to two-speaker dialogue when filler_words is enabled; the default is off and a single voice is unaffected.
How do I control the delivery?
Direct Gemini 3.8 Flash-Lite TTS with instructions for mood and delivery, using style, accent, pace and scene where needed; listen to a preview because generative speech may interpret a cue differently.
Can I use Fola or Neno?
The Gemini 3.8 Flash-Lite TTS preset library exposes 70 voices with Kore as the default; assign voice_id separately for each named dialogue speaker.
Can I clone a voice?
On SpicyAPI, Gemini 3.8 Flash-Lite TTS temporary cloning requires dialogue and an adult owner’s reference_audio_url plus consent_audio_url, without voice_id: WAV files up to 10 MB each, a 10–30-second natural reference, the same microphone and room, and the prescribed spoken consent; AI recordings are excluded and owner-supplied recordings have not yet verified this path.
Does availability grant content permissions?
In SpicyAPI tests, Gemini 3.8 Flash-Lite TTS read the submitted adult scripts without omissions; that observation is not a guarantee, and you remain responsible for recording rights, informed consent and lawful publication without impersonation.
Gemini 3.8 Flash-Lite TTS is billed by measured audio seconds; the running task holds 660 seconds of balance and releases the unused amount after measurement, while failed requests are not charged.
In SpicyAPI tests, Gemini 3.8 Flash-Lite TTS read the submitted adult scripts without omissions; that observation is not a guarantee, and you remain responsible for recording rights, informed consent and lawful publication without impersonation. Use Gemini 3.8 Flash-Lite TTS only with lawful, consensual adult material; content involving minors is prohibited.
Gemini 3.8 Flash-Lite TTS — consent_audio_url: “I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.”
In SpicyAPI tests, Gemini 3.8 Flash-Lite TTS read the submitted adult scripts without omissions; that observation is not a guarantee, and you remain responsible for recording rights, informed consent and lawful publication without impersonation. Use Gemini 3.8 Flash-Lite TTS only with lawful, consensual adult material; content involving minors is prohibited.
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: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "google/gemini-3.8-flash-lite-tts/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"voice_id": "Kore"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.













