Use the OpenAI TTS API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/openai_tts/text_to_speech \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-1-hd",
"text": "Convert this product onboarding script into clear, natural speech for an in-app walkthrough."
}'import { OpenaiTtsClient } from "@runapi.ai/openai-tts";
const client = new OpenaiTtsClient();
const result = await client.textToSpeech.run({
model: "tts-1-hd",
text: "Convert this product onboarding script into clear, natural speech for an in-app walkthrough.",
});require "runapi/openai_tts"
client = RunApi::OpenaiTts::Client.new
result = client.text_to_speech.run(
model: "tts-1-hd",
text: "Convert this product onboarding script into clear, natural speech for an in-app walkthrough."
)npx skills add runapi-ai/openai-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 cursorOpenAI TTS converts text into speech through a synchronous RunAPI endpoint. Choose tts-1 for latency-sensitive applications or tts-1-hd for higher-fidelity narration; both return a managed MP3 URL.
| Endpoint | Resolution | Duration | Price | |
|---|---|---|---|---|
| text_to_speech | — | — | $0.02 / 1K UTF-8 bytes |
Prices shown for tts-1. 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.
OpenAI TTS provides focused text-to-speech models for interactive playback and polished narration. Through RunAPI, both variants share one request shape and return managed audio metadata.
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.
tts-1 prioritizes low latency for interactive playback, while tts-1-hd prioritizes higher audio quality for narration and finished content.
Both variants return MP3 audio with format, MIME type, and byte-size metadata in the RunAPI response.
Yes. RunAPI validates the audio and returns a managed URL instead of exposing a temporary source URL.
The initial endpoint uses the published default voice and speed. Custom voice and speed controls are not part of this endpoint contract.
Yes. A successful request returns the completed audio result directly, without a separate polling endpoint.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.