Voices™ by Sound Studio Pro

Text-to-speech API. Turn text into natural speech — dozens of voices, one REST API, free tier. Get your API key. Did you use Voices?

Free tier: 10,000 characters/month to test

Get Voices™ API Key Pricing Try Voices™

Easy Voices™ API Integration

List voices with a single GET (no key required). Synthesize speech with POST and your API key. WAV or MPEG.

# List voices (no key required)
GET https://soundstudiopro.com/api/voice/v1/voices.php

# Synthesize speech
POST https://soundstudiopro.com/api/voice/v1/speech.php
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "text": "Hello world",
  "voice_id": "Suad Qasim",
  "language_id": "en",
  "speed": 1.0,
  "temperature": 0.2,
  "volume": 1.0,
  "output_format": "wav",
  "output_format": "wav",
  "stream": false
}

# Optional body params (or query): output_format = "mp3" | "wav" (default wav).
# Optional: stream = true — response is sent chunked for lower perceived latency.

Body: text, voice_id, language_id (e.g. en, es). Optional: speed (0.5–2.0, default 1), temperature (0.1–1.0, expression: lower = stable, higher = expressive), volume (0.25–3.0 multiplier), output_format — wav (default) or mp3. stream — set to true for chunked response. 

# Voice design — get recommended voices from a short description (no key)
POST https://soundstudiopro.com/api/voice/v1/design.php
Content-Type: application/json

{
  "description": "calm female voice for meditation",
  "num_candidates": 3
}

# Returns: { "candidates": [ { "voice_id", "name", "slug", "category", "tags", "preview_text" } ] }
# Use any returned voice_id in the speech endpoint.
# Voice clones — upload your voice samples (session auth)
GET  https://soundstudiopro.com/api/voice/v1/clones.php          # List your clones
POST https://soundstudiopro.com/api/voice/v1/clones.php          # Create: multipart name + file (or files[])
     Form: name=My voice, file=@sample.wav  (WAV or MP3, max 15 MB, up to 5 files)
DELETE https://soundstudiopro.com/api/voice/v1/clones.php        # Body: { "id": 7 } — remove clone
# When a clone is ready, use voice_id "clone_7" in the speech endpoint.

Key Features

Everything you need for text-to-speech in your app.

🔊

50+ Voices

Our voice library. Unique names, natural sound. All included — no per-voice upsell.

⚙

Simple REST API

One endpoint to list voices, one to synthesize. No SDK required. Use any language or tool.

🎵

WAV & MPEG

Get audio back in standard formats. Ideal for apps, IVR, accessibility, and content creation.

💰

Free Tier

10,000 characters per month free. Metered usage, transparent limits. Upgrade when you scale.

Why Use Voices™

Built for developers who want reliable TTS without lock-in.

Your key, your usage

Create API keys in the dashboard. Track usage per key. Revoke anytime. No vendor lock-in.

Stable & documented

REST API with clear request/response. List voices and synthesize in one call. Full docs in the dashboard.

Commercial use

Use generated audio in your products, apps, and content. No watermarks, no extra fees per voice.

Pricing

Transparent, character-based usage. Free tier to get started.

Plan Characters / month Description
Free 10,000 Included. Create an account and get your API key to start.
Paid Higher limits Upgrade when you need more. Metered usage, no hidden fees.

Frequently Asked Questions

Can I try Voices™ for free?
Yes. Sign up, create an API key in the Voices™ API keys dashboard, and you get 10,000 characters per month on the free tier to test.
How do I get a Voices™ API key?
Log in, go to Voices™ API keys (or /voice/keys), and create a key. Use it in the Authorization: Bearer YOUR_KEY header when calling the speech endpoint.
Where is the API documentation?
After creating an API key, the dashboard shows endpoints, request format, and usage. List voices: GET /api/voice/v1/voices.php. Synthesize: POST /api/voice/v1/speech.php with JSON body.
Is this the same as the Music API?
No. The Music API (soundstudiopro.com/api) is for AI music generation. Voices™ is for text-to-speech only. Different keys: get Music API keys at api_keys.php, Voices™ API keys at /voice/keys.
Can I create a voice from my own voice (voice cloning)?
Yes. In the Dashboard, open My Clones, upload a voice sample (WAV or MP3, clear speech, 30 seconds or more works best). Once the clone is ready, you get a voice_id (e.g. clone_7) and use it in the speech API exactly like any built-in voice. Your custom voice also appears on the Voices page under My Clones.

Ready to Get Started?

Create an account, get your Voices™ API key, and start building.

Get Your Voices™ API Key