Gemini 3.8 Flash-Lite TTS Review: 30 Voices, with Limits on Cue Tags
One or two voices per request: up to 5,000 characters of script for one voice, or up to 20 dialogue lines of 250 characters each for two.
One or two voices per request: up to 5,000 characters of script for one voice, or up to 20 dialogue lines of 250 characters each for two.
- Lydia
- Not hands-on tested · catalogue checked Oct 7, 2026
- Updated Oct 7, 2026
The verdict
We did not create new paid samples for this article. Published examples remain examples of a particular input and output, rather than a statistically controlled comparison. The illustration accompanying this article is editorial artwork, not a sample produced by the reviewed model.
What we liked and what held it back
What we liked
- 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. Keep the voice selection and delivery notes fixed, then listen for changes between chapters. Check each chapter’s ending against its script before assembling the narration.
What held it back
- One or two voices per request: up to 5,000 characters of script for one voice, or up to 20 dialogue lines of 250 characters each for two. Bracketed cues are not reliably performed — the model sometimes reads the tag aloud. The model stops at 16,384 audio tokens per clip. Output is a single WAV file (24 kHz, 16-bit mono); word timings and subtitles are not returned. Only the 30 prebuilt voices are offered — no cloning, no voice design. The language of the script is detected automatically and cannot be forced.
What the evidence shows
On 30 September 2026, the Artificial Analysis native-voice leaderboard listed this exact model at 1240 Elo, with a 95% interval of 1225–1255 and 2232 votes. This measures listener preference using each model’s own voices; it is an external model benchmark, not an experiment on this SpicyAPI endpoint. Votes are not independent scripts, and an Elo difference is not a percentage improvement.
The result is useful when naturalness matters, but it does not establish pronunciation accuracy on your vocabulary, voice-clone similarity, long-form consistency, every supported language, or response time here. Choose a voice you will actually use, then check your real script. Do not substitute a similarly named HD, Flash or older version for the entry above.
A practical starting brief
The following is a starting input adapted from the model’s published examples, not a promise that every run will sound the same. Keep the words and delivery directions separate wherever the endpoint offers separate fields. Preview an ordinary sentence before extending the script; adding more adjectives rarely resolves an ambiguous instruction.
{
"text": "Hey... it's me. Mmm... I know it's late. I just wanted to hear your voice before I fall asleep. Call me back?",
"voice_id": "Enceladus"
}Start with the material that determines acceptance: a name, a difficult number, a sentence with an emotional turn, or the passage you cannot afford to misread. Listen or read against the original, including the ending. Keep the input fixed while changing one control, so a difference in wording does not get mistaken for a better model. A pleasant voice alone does not prove that every word survived.
Read the current quote on the model task page before submitting. Per-character, per-second and per-request billing cannot be compared by the displayed starting number alone. Compare the same passage or recording, and include any format conversion or alignment you still need to do.
How to choose an alternative
Choose by the missing capability before comparing a headline quality number. An alternative should remove a concrete bottleneck—voice selection, a longer script, delivery direction or the right kind of transcription—rather than simply have a newer name. The current pages below show their actual tasks and price units.
What Gemini 3.8 Flash-Lite TTS can do on SpicyAPI
Straight from the live model specification on SpicyAPI. Some creators offer more in their own apps; this is what you can call through our API today.
| Feature | Text to speech |
|---|---|
| Seed control | No |
| Negative prompt | No |
What do you think?
Was this review useful?
Log in to vote.
Comments
Comments are checked automatically and by our team. We remove spam, offensive content, personal attacks and anything that names a real person without consent. Report a comment and we review it within one business day.
Tried this model? Share what worked. You need a free account to comment, so we can keep spam out.
Gemini 3.8 Flash-Lite TTS FAQ
Try Gemini 3.8 Flash-Lite TTS yourself
Set every parameter in the Playground and see the exact price before you run it.
More reviews
See the leaderboards →
Gemini 3.8 Flash TTS
One or two voices per request: up to 5,000 characters of script for one voice, or up to 20 dialogue lines of 250 characters each for two.
Not hands-on tested · catalogue checked Oct 7, 2026
Read the review
Seed Speech 2.0
One voice per request, up to 5,000 characters of script.
Not hands-on tested · catalogue checked Oct 7, 2026
Read the review
Grok TTS
One voice per request, up to 15,000 characters of script.
Not hands-on tested · catalogue checked Oct 7, 2026
Read the review