Gemini 3.8 Flash Text-to-Speech generates expressive speech from text with configurable voice and delivery-style controls for narration, dialogue, localization, virtual assistants, and voice production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.05per run·~20 / $1
Gemini 3.8 Flash Text-to-Speech generates expressive speech from text with 30 preset voices and natural-language control over delivery. Use style instructions to guide tone, pacing, accent, and emotion without embedding delivery directions into the spoken text.
The endpoint supports both standard single-speaker narration and API-based two-speaker dialogue, making it suitable for voiceovers, conversations, character dialogue, narration, and other speech-generation workflows.
Expressive text-to-speech
Generate natural speech from text with control over tone, pacing, accent, and emotional delivery.
30 preset voices
Choose from a broad set of built-in voices for different narration and character styles.
Natural-language style control
Describe how the speech should be delivered through style_instructions.
Single-speaker narration
Generate voiceovers, narration, explanations, and other single-speaker speech.
Per-turn delivery control
Dialogue turns can include their own style_instructions for different emotions or speaking styles.
WAV output
Receive the generated speech as a downloadable WAV audio file.
| Parameter | Required | Description |
|---|---|---|
| text | Conditional | Text to speak for single-speaker generation. Supports up to 8000 characters. Omit when using dialogue mode. |
| voice | No | Preset voice for single-speaker speech. Default: Kore. |
| style_instructions | No | Optional natural-language instructions for tone, pacing, accent, emotion, or other delivery characteristics. Supports up to 2000 characters. |
| speakers | Conditional | Define exactly 2 speakers with distinct speaker_id values and their selected voices. |
| turns | Conditional | Each turn contains a speaker_id, text, and optional style_instructions. |
Kore.speaker_id values and assign a voice to each.style_instructions for overall delivery guidance.| Billable Characters | Price |
|---|---|
| 100 | $0.05 |
| 1,000 | $0.05 |
| 5,000 | $0.25 |
For single-speaker generation, billable characters include:
textstyle_instructionsFor dialogue generation, billable characters include:
turnsstyle_instructionsstyle_instructionstext or turns and put delivery directions in style_instructions.speaker_id used in turns has been configured in speakers.8192-token input limit.<laugh> or <sigh> can be used when they are part of the intended performance.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/google/gemini-3.8-flash/text-to-speech with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Gemini 3.8 Flash Text To Speech below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"voice": "Kore"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/google/gemini-3.8-flash/text-to-speech" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/google/gemini-3.8-flash/text-to-speech";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"voice": "Kore"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"voice": "Kore"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/google/gemini-3.8-flash/text-to-speech", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Gemini 3.8 Flash Text To Speech is a Google model for audio generation, exposed as a REST API on WaveSpeedAI. Gemini 3.8 Flash Text-to-Speech generates expressive speech from text with configurable voice and delivery-style controls for narration, dialogue, localization, virtual assistants, and voice production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/google/google-gemini-3.8-flash-text-to-speech.
Gemini 3.8 Flash Text To Speech starts at $0.05 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `text`, `voice`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/google/google-gemini-3.8-flash-text-to-speech.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (Google). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.