Documentation Index

Fetch the complete documentation index at: https://docs.supertoneapi.com/llms.txt

Use this file to discover all available pages before exploring further.

​

Empowering Voices, Simplifying AI Integration

​

As simple as it sounds

from supertone import Supertone

with Supertone(api_key=API_KEY) as client:
    response = client.text_to_speech.create_speech(
        voice_id=VOICE_ID,
        text="Hello from Supertone.",
        language="en",
    )
    open("speech.wav", "wb").write(response.result.read())

import { Supertone } from "@supertone/supertone";

const client = new Supertone({ apiKey: API_KEY });
const response = await client.textToSpeech.createSpeech({
  voiceId: VOICE_ID,
  apiConvertTextToSpeechUsingCharacterRequest: {
    text: "Hello from Supertone.",
    language: "en",
  },
});

curl -X POST "https://supertoneapi.com/v1/text-to-speech/$VOICE_ID" \
  -H "x-sup-api-key: $SUPERTONE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from Supertone.", "language": "en"}' \
  --output speech.wav

​

Built for production

• ✅ 31 languages with character identity preserved across each one
• ✅ 150+ premium voices, with 50+ emotional styles
• ✅ Voice cloning from ~10-second audio samples
• ✅ TTS models for every use case — from flagship quality (sona_speech_2) to ultra-low latency with high speech stability (supertonic_api_3)
• ✅ Fully adjustable pitch, intonation, and speed via voice_settings
• ✅ Official Python & TypeScript SDKs with auto-chunking, retries, and async support

​

What you can build

​

Get started