Migrating from Sora or DALL-E? Use promo code DALLE1000 for $10 in free API credits!
CreativeAI
voiceCreativeAINew

Voice TTSNatural-sounding text-to-speech with 6 voices and 10 languages

Voice TTS is CreativeAI's text-to-speech model, delivering natural-sounding audio in 6 distinct voice presets (Alloy, Echo, Fable, Onyx, Nova, Shimmer) across 10 languages. Adjustable speed control (0.5×–2.0×) and fast generation (~2–5 seconds) make it ideal for product videos, voiceovers, multilingual content, and accessibility workflows.

Specifications

Output FormatMP3 Audio
Voices6 presets
Languages10
Speed Control0.5×–2.0×
Average Speed~2–5 seconds
Credits8 credits per generation

Capabilities

Natural-sounding text-to-speech
6 voice presets (Alloy, Echo, Fable, Onyx, Nova, Shimmer)
10 languages (EN, ZH, JA, KO, ES, FR, DE, PT, RU, AR)
Adjustable speed control (0.5×–2.0×)
Fast generation (~2–5 seconds)
OpenAI-compatible API endpoint

Quick Start

Start generating with Voice TTS in seconds. OpenAI SDK compatible — just change the base URL.

curl
curl -X POST https://api.creativeai.run/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Welcome to CreativeAI. Generate images, videos, and voice with one API.",
    "voice": "alloy",
    "language": "en",
    "speed": 1.0
  }'

Use Cases

What creators are building with Voice TTS

Product video voiceovers

Multilingual marketing content

Podcast and audiobook prototyping

E-commerce product descriptions (audio)

Accessibility and screen-reader alternatives

Tutorial and documentation narration

Ready to create with Voice TTS?

Start with 50 free credits. No credit card required.

8 credits per generation · Pay-as-you-go or subscribe · OpenAI SDK compatible