Text-to-speech API
Pre-launch
Text in.Speech out.
Send text and an API key over HTTP. Get an audio file back, spoken by voice models we build ourselves.
Not open for sign-up yet. Pricing, voices and a launch date will be announced when they are ready.
An illustration. There are no audio samples to play yet.
API
Preview The planned API. Details may change before launch.
Plain HTTP. No SDK.
Call it from the code you already have, in any language that can make an HTTP request.
- API key
Authorization: Bearer $KRUEAM_API_KEY- Not open yetCreate a key in the Studio and keep it in a server-side environment variable, never in code that ships to users.
- Request
POST https://api.krueamartwork.com/v1/speech{"voice": "<voice-id>", "text": "สวัสดีครับ"}- Send the text and a voice id as JSON, with the key in the Authorization header.
- Response
- An audio file
- Save it, play it in your app, or pass it on to your users. File formats will be listed in the docs at launch.
Code sample
curl
curl -X POST \ https://api.krueamartwork.com/v1/speech \ -H "Authorization: Bearer $KRUEAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{"voice": "<voice-id>", "text": "สวัสดีครับ"}' \ -o speech # The response body is the audio file. Formats: see the docs at launch.Python
import osimport requests key = os.environ["KRUEAM_API_KEY"]resp = requests.post( "https://api.krueamartwork.com/v1/speech", headers={"Authorization": f"Bearer {key}"}, json={ "voice": "<voice-id>", "text": "สวัสดีครับ", },)resp.raise_for_status() # The response body is the audio file. Formats: see the docs at launch.with open("speech", "wb") as f: f.write(resp.content)JavaScript
import { writeFile } from "node:fs/promises"; const url = "https://api.krueamartwork.com/v1/speech";const key = process.env.KRUEAM_API_KEY; const res = await fetch(url, { method: "POST", headers: { Authorization: `Bearer ${key}`, "Content-Type": "application/json", }, body: JSON.stringify({ voice: "<voice-id>", text: "สวัสดีครับ", }),}); // The response body is the audio file. Formats: see the docs at launch.const audio = await res.arrayBuffer();await writeFile("speech", Buffer.from(audio));Studio
In progress
Hear it in the browser. Then write the code.
Once you log in, the Studio is where you try voices, manage API keys, check usage and read the docs.
What is in the Studio
- Playground
- Type some text, pick a voice and listen to the result before it goes into your code.
- API keys
- Create and manage the keys you call the API with.
- Usage
- See how much each key has been used.
- Docs
- API reference and code samples in several languages.
The Studio is still being built. Details may change before launch.
Contact
Not open yet. Talk to us anyway.
Want to hear when sign-up opens, or tell us what you would use generated speech for? Send us an email.
Email the teamhello@krueamartwork.com