How to Generate Speech

Convert text to natural-sounding speech using Get3W's text-to-speech models.

Quick Start

cURL

curl -X POST "https://api.get3w.com/api/v3/minimax/speech-02-hd" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to Get3W, the unified AI platform.",
    "voice_id": "default"
  }'

Python

import get3w

output = get3w.run(
    "minimax/speech-02-hd",
    {
        "text": "Welcome to Get3W, the unified AI platform.",
        "voice_id": "default"
    }
)

print(output["outputs"][0])

JavaScript

const output = await client.run("minimax/speech-02-hd", {
    text: "Welcome to Get3W, the unified AI platform.",
    voice_id: "default",
});

console.log(output.outputs[0]);

Available Models

Model	Quality	Speed	Languages
Minimax Speech 02	High	Fast	Multi-language
ElevenLabs V3	Very High	Medium	Multi-language
ElevenLabs Flash	Good	Fast	Multi-language

Common Parameters

Parameter	Type	Description	Default
text	string	The text to convert to speech	Required
voice_id	string	Voice identifier	default
speed	number	Speech speed multiplier	1.0
language	string	Language code (e.g., "en")	auto

Voice Cloning

Clone a voice from an audio sample:

curl -X POST "https://api.get3w.com/api/v3/elevenlabs/voice-changer" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://cdn.get3w.com/uploads/voice-sample.mp3",
    "text": "This is a cloned voice speaking."
  }'

Next Steps

• How to Create a Digital Human — Combine speech with avatars
• How to Create Video from Image — Add visuals to your audio