Introduction
Gemini 2.5 Pro TTS suits carefully directed narration, with 30 preset voices and a 5,000-character script limit on SpicyAPI.
| Field | Value |
|---|---|
| Input | Text |
| Output | Audio |
| Required field | text (1 to 5,000 characters) or dialogue (up to 20 lines) |
| Optional fields |
|
| Result | One WAV file, 24 kHz, 16-bit, mono |
| Longest clip | About 655 seconds (16,384 audio tokens) |
| Billed quantity | Gemini 2.5 Pro 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 2.5 Pro TTS take, place only the spoken script in text, up to 5,000 characters, and keep delivery direction in instructions. at least 1 characters · at most 5000 characters |
dialogue | No | A scripted conversation for up to two voices, used instead of text: up to 20 lines, each with speaker (a name from speakers) and text of up to 250 characters. at least 1 items · at most 20 items |
speakers | No | The cast for dialogue: one or two entries, each with a name the lines refer to, a |
voice_id | No | One of 30 prebuilt voices, each with a fixed character. Defaults to Kore. |
style | No | Set style for the overall performance of your chosen Gemini 2.5 Pro TTS voice; a dialogue speaker’s own style takes precedence over this shared direction. |
pace | No | For Gemini 2.5 Pro TTS, pace offers natural, |
accent | No | Choose an English accent for the 30-voice Gemini 2.5 Pro TTS library with accent; in dialogue this supplies the fallback for speakers without their own accent. |
instructions | No | Free-text direction on how to read: pace, mood, distance from the microphone, who is listening. Shapes the delivery and is not spoken. at most 1000 characters |
scene | No | Where and to whom the words are spoken, such as “a quiet hotel room after midnight”. Shapes the delivery and is not spoken. at most 500 characters |
temperature | No | For repeat Gemini 2.5 Pro TTS recordings, temperature ranges from 0 to 2 and higher values increase delivery variation; omit it for the model default without changing the per-se… |
Pricing
$0.00045 / second
Gemini 2.5 Pro 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
Audiobooks and long-form narration
For Gemini 2.5 Pro TTS narration, split a book into scripts within the 5,000-character limit and keep the same preset voice and direction across sections.
Character and companion voices
Give a Gemini 2.5 Pro TTS character a preset voice, then use short spoken sentences and instructions to distinguish an intimate aside from a narrated passage.
Uncensored audio stories
In SpicyAPI tests, Gemini 2.5 Pro 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 2.5 Pro 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
Send the script in text
Write it exactly as it should be spoken, including punctuation for pauses. Up to 5,000 characters.
Pick a voice and, if needed, a style and accent
voice_iddefaults to Kore and accent to neutral. Add style only when you want a specific manner, such as whisper.Direct the reading in instructions
One or two sentences on pace, mood and who is listening work better than a list of adjectives. The note is not read aloud.
Gemini 2.5 Pro TTS suits carefully directed narration, with 30 preset voices and a 5,000-character script limit on SpicyAPI.
Audiobooks and long-form narration
For Gemini 2.5 Pro TTS narration, split a book into scripts within the 5,000-character limit and keep the same preset voice and direction across sections.
Character and companion voices
Give a Gemini 2.5 Pro TTS character a preset voice, then use short spoken sentences and instructions to distinguish an intimate aside from a narrated passage.
Uncensored audio stories
In SpicyAPI tests, Gemini 2.5 Pro 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 2.5 Pro TTS WAV as the voice track for an avatar or lip-sync step, checking its measured duration before setting the video timeline.
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. The model stops at 16,384 audio tokens, about 655 seconds, so very slow deliveries of long scripts end there. Output is a single WAV file (24 kHz, 16-bit mono); there are no word timings, no subtitles and no other formats. Only the 30 prebuilt voices are offered — no cloning, no custom voices. The language of the script is detected automatically and cannot be forced.
In SpicyAPI tests, Gemini 2.5 Pro 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 30-voice Gemini 2.5 Pro TTS library with accent; in dialogue this supplies the fallback for speakers without their own accent.
dialogue
A scripted conversation for up to two voices, used instead of text: up to 20 lines, each with speaker (a name from speakers) and text of up to 250 characters. Lines are performed in order. Billed per second of audio returned, like text.
instructions
Free-text direction on how to read: pace, mood, distance from the microphone, who is listening. Shapes the delivery and is not spoken. Up to 1,000 characters.
pace
For Gemini 2.5 Pro TTS, pace offers natural, rapid_fire, the_drift and staccato; slower readings use more billable seconds even when the 5,000-character script stays the same.
scene
Where and to whom the words are spoken, such as “a quiet hotel room after midnight”. Shapes the delivery and is not spoken. Up to 500 characters. Does not change the price per second.
speakers
The cast for dialogue: one or two entries, each with a name the lines refer to, a voice_id, and optionally accent, style, pace and profile (a short description of who is speaking, which is not read aloud). Anything a speaker leaves out falls back to the top-level accent, style and pace. Does not change the price per second.
style
Set style for the overall performance of your chosen Gemini 2.5 Pro TTS voice; a dialogue speaker’s own style takes precedence over this shared direction.
temperature
For repeat Gemini 2.5 Pro 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 2.5 Pro TTS take, place only the spoken script in text, up to 5,000 characters, and keep delivery direction in instructions.
voice_id
One of 30 prebuilt voices, each with a fixed character. Defaults to Kore. It voices text; in dialogue each speaker sets its own voice_id.
Will Gemini 2.5 Pro TTS speak the instructions field?
No. instructions only shapes the delivery — pace, mood, closeness to the microphone. Only text is spoken.
Which languages does it read?
It detects the language of the script automatically; there is no language setting. The voices keep their character across languages, and accent only affects English.
Why is there a hold on my balance while it runs?
The length of the audio is only known once it exists, so the task holds enough for the longest clip the model can produce (660 seconds) and releases the difference when the audio is measured. You are charged only for the seconds returned.
Are scripts filtered or softened?
In SpicyAPI tests, Gemini 2.5 Pro 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 2.5 Pro 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 2.5 Pro 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 2.5 Pro TTS only with lawful, consensual adult material; content involving minors is prohibited.
In SpicyAPI tests, Gemini 2.5 Pro 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 2.5 Pro 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: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "google/gemini-2.5-pro-tts/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"accent": "neutral",
"voice_id": "Kore"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.













