Google Gemini 3.8 Flash Text To Speech API Documentation

Google Gemini 3.8 Flash Text To Speech API Documentation

Playground

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.

Features

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.

Why Choose This?

• 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.

Parameters

How to Use

Single-Speaker Speech

1. Enter the text — Provide the content you want spoken.
2. Choose a voice optional — Select one of the available preset voices or keep the default Kore.
3. Add style instructions optional — Describe the desired tone, pacing, accent, emotion, or delivery.
4. Submit — Generate the speech and retrieve the WAV audio.

Two-Speaker Dialogue

1. Configure two speakers — Define exactly two distinct speaker_id values and assign a voice to each.
2. Create ordered turns — Add each speaker’s dialogue in the order it should be spoken.
3. Add per-turn style optional — Give individual turns their own delivery instructions when needed.
4. Add global style optional — Use style_instructions for overall delivery guidance.
5. Submit — Generate the complete two-speaker dialogue as audio.

Pricing

For single-speaker generation, billable characters include:

• text
• style_instructions

For dialogue generation, billable characters include:

• Text from all turns
• Per-turn style_instructions
• Global style_instructions

Best Use Cases

• Narration and voiceovers — Generate expressive speech for videos, presentations, explainers, and other media.
• Two-speaker conversations — Create API-driven dialogue between two configured voices.
• Character dialogue — Give different speakers distinct voices and delivery styles.
• Audiobook and storytelling workflows — Control pacing, emotion, and narration style through natural-language instructions.
• Educational content — Generate clear spoken explanations, lessons, and instructional audio.
• Localized voice content — Guide accent, tone, and delivery through style instructions.
• Conversational prototypes — Create spoken interactions for assistants, characters, demos, and dialogue experiences.

Pro Tips

• Keep the spoken content in text or turns and put delivery directions in style_instructions.
• Use short, specific style instructions for more consistent delivery.
• Describe concrete characteristics such as pace, emotional tone, energy, or accent instead of vague style requests.
• In dialogue mode, make sure every speaker_id used in turns has been configured in speakers.
• Use per-turn style instructions when a speaker’s emotion or delivery changes during the conversation.
• Keep the total request within the 8192-token input limit.
• Inline vocal events such as <laugh> or <sigh> can be used when they are part of the intended performance.

Related Models

• Gemini 3.8 Flash Lite Text-to-Speech — Generate speech with the lighter Gemini 3.8 Flash Lite text-to-speech endpoint.
• Gemini 3.8 Flash Text-to-Speech — Generate expressive single-speaker or two-speaker speech with preset voices and natural-language delivery control.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-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 "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters