Skip to main content
ArtEmotion
Audio

Gemini 3.8 Flash TTS

Credit-based pricing.

Gemini 3.8 Flash TTS preview
Output
audio
Duration
15s, 30s, 60s, 120s, 300s, 600s

Example prompt

Take a breath. <short pause> Your next great idea starts here.
Try this prompt →
LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=google/gemini-3.8-flash-tts.

POST/api/v1/generate12 fields · 2 required
FieldTypeRequirementContract
model_idconstantRequiredArtEmotion model identifier.
extraobjectOptionalModel-specific settings may also be nested here.
max_creditsnumberOptionalReject before submission if the estimated list price exceeds this cap. · Range: 1–…
webhook_urlstringOptionalFormat: uri
webhook_secretstringOptionalOptional model input.
folder_idstringOptionalOptional model input.
promptstringRequiredExact speech text. Inline vocal tags are supported. Combined script, repeated turn styles and settings must fit within 7,000 UTF-8 bytes.
voicestringOptionalPrebuilt voice for single-speaker narration. Dialogue uses the speaker mapping below. · Allowed: Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Puck, Pulcherrima, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi · Default: Kore
speakersarray<object>OptionalOmit for narration. For dialogue, supply exactly two unique speaker names; every script line must start with a configured Name: prefix. · Items: 0–2
style_instructionsstringOptionalUp to 500 characters. E.g. warm, conversational, speaking slowly. These directions are not spoken aloud. · Default:
temperaturenumberOptionalDefault: 1 · Range: 0–2
durationnumberOptionalAudio-token budget expressed in seconds, billed as a fixed quoted allowance. Output may be shorter or cut off at this cap. · Allowed: 15, 30, 60, 120, 300, 600 · Default: 60
Minimal request example
{
  "model_id": "google/gemini-3.8-flash-tts",
  "prompt": "Take a breath. <short pause> Your next great idea starts here."
}
Raw JSON Schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=google%2Fgemini-3.8-flash-tts",
  "title": "Gemini 3.8 Flash TTS generation request",
  "description": "Request body accepted by POST /api/v1/generate for google/gemini-3.8-flash-tts.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "google/gemini-3.8-flash-tts",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string",
      "minLength": 1,
      "maxLength": 5000,
      "description": "Exact speech text. Inline vocal tags are supported. Combined script, repeated turn styles and settings must fit within 7,000 UTF-8 bytes."
    },
    "voice": {
      "title": "Voice",
      "description": "Prebuilt voice for single-speaker narration. Dialogue uses the speaker mapping below.",
      "default": "Kore",
      "type": "string",
      "enum": [
        "Achernar",
        "Achird",
        "Algenib",
        "Algieba",
        "Alnilam",
        "Aoede",
        "Autonoe",
        "Callirrhoe",
        "Charon",
        "Despina",
        "Enceladus",
        "Erinome",
        "Fenrir",
        "Gacrux",
        "Iapetus",
        "Kore",
        "Laomedeia",
        "Leda",
        "Orus",
        "Puck",
        "Pulcherrima",
        "Rasalgethi",
        "Sadachbia",
        "Sadaltager",
        "Schedar",
        "Sulafat",
        "Umbriel",
        "Vindemiatrix",
        "Zephyr",
        "Zubenelgenubi"
      ]
    },
    "speakers": {
      "title": "Speakers",
      "description": "Omit for narration. For dialogue, supply exactly two unique speaker names; every script line must start with a configured Name: prefix.",
      "type": "array",
      "maxItems": 2,
      "oneOf": [
        {
          "maxItems": 0
        },
        {
          "minItems": 2,
          "maxItems": 2
        }
      ],
      "items": {
        "type": "object",
        "additionalProperties": false,
        "required": [
          "speaker",
          "voice"
        ],
        "properties": {
          "speaker": {
            "type": "string",
            "minLength": 1,
            "maxLength": 40,
            "pattern": "^[^:\\r\\n]+$"
          },
          "voice": {
            "type": "string",
            "enum": [
              "Achernar",
              "Achird",
              "Algenib",
              "Algieba",
              "Alnilam",
              "Aoede",
              "Autonoe",
              "Callirrhoe",
              "Charon",
              "Despina",
              "Enceladus",
              "Erinome",
              "Fenrir",
              "Gacrux",
              "Iapetus",
              "Kore",
              "Laomedeia",
              "Leda",
              "Orus",
              "Puck",
              "Pulcherrima",
              "Rasalgethi",
              "Sadachbia",
              "Sadaltager",
              "Schedar",
              "Sulafat",
              "Umbriel",
              "Vindemiatrix",
              "Zephyr",
              "Zubenelgenubi"
            ]
          }
        }
      }
    },
    "style_instructions": {
      "title": "Delivery Style",
      "description": "Up to 500 characters. E.g. warm, conversational, speaking slowly. These directions are not spoken aloud.",
      "default": "",
      "type": "string",
      "maxLength": 500
    },
    "temperature": {
      "title": "Temperature",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 2,
      "multipleOf": 0.05
    },
    "duration": {
      "type": "number",
      "title": "Audio Budget (up to seconds)",
      "description": "Audio-token budget expressed in seconds, billed as a fixed quoted allowance. Output may be shorter or cut off at this cap.",
      "default": 60,
      "enum": [
        15,
        30,
        60,
        120,
        300,
        600
      ]
    }
  },
  "required": [
    "model_id",
    "prompt"
  ],
  "additionalProperties": false
}

FAQ

How much does Gemini 3.8 Flash TTS cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if Gemini 3.8 Flash TTS fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call Gemini 3.8 Flash TTS from the API?

Yes. Use POST /api/v1/generate with model_id: "google/gemini-3.8-flash-tts". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with Gemini 3.8 Flash TTS?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.