Use the Gemini TTS API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/gemini_tts/text_to_speech \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-tts",
"text": "Generate a two-speaker podcast introduction with a calm British host and an energetic American guest."
}'import { GeminiTtsClient } from "@runapi.ai/gemini-tts";
const client = new GeminiTtsClient();
const result = await client.textToSpeech.run({
model: "gemini-3.1-flash-tts",
text: "Generate a two-speaker podcast introduction with a calm British host and an energetic American guest.",
});require "runapi/gemini_tts"
client = RunApi::GeminiTts::Client.new
result = client.text_to_speech.run(
model: "gemini-3.1-flash-tts",
text: "Generate a two-speaker podcast introduction with a calm British host and an energetic American guest."
)npx skills add runapi-ai/gemini-tts -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorGemini TTS turns ordered dialogue into speech while preserving a separate voice configuration for each speaker. Requests can also set the scene, overall delivery context, and sampling temperature.
| Endpoint | Resolution | Duration | Price | |
|---|---|---|---|---|
| text_to_speech | — | — | Input $1.40 / 1M tokens | Output $28.00 / 1M tokens |
Prices shown for gemini-2.5-pro-tts. Other variants retain their own endpoint pricing.
Sign up and generate an API key from the dashboard.
Choose the version that best matches your quality and cost requirements.
Submit your prompt and parameters to the model's documented endpoint.
Poll the task or set a webhook, then download the completed output.
Gemini TTS belongs to the Google catalog on RunAPI and exposes Gemini 2.5 Pro TTS and Gemini 3.1 Flash TTS through one consistent API, SDK, and CLI surface.
A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.
RunAPI supports Gemini 2.5 Pro TTS and Gemini 3.1 Flash TTS through the same text-to-speech endpoint and request shape.
Add a speaker configuration for each participant using a unique Speaker N identifier, then assign each dialogue turn to one of those identifiers.
Each speaker has a voice, accent, delivery style, and pace, with an optional audio profile for additional voice direction.
Scene describes the recording environment, while sample context sets the overall tone and delivery guidance for the dialogue.
Query the task or receive its callback after completion; the response contains an audios list with the generated file URL.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.