Build/Tools/Text to Speech
AI-powered5 credits / callPOST /api/v1/tools/tts

Text to Speech

OpenAI TTS-1-HD — 6 voices, 6 audio formats

Convert text to natural-sounding audio using OpenAI TTS-1-HD. Choose from 6 voices (alloy, echo, fable, onyx, nova, shimmer), 6 output formats, and speed from 0.25× to 4×. Returns raw audio binary.

How it works

POSTs your text to TTS-1-HD and streams back the audio file. Response headers include voice, format, processing time, and estimated audio duration.

What you could build

ArticleVoice
Listen to any article — browser extension with TTS
$1K–$3K MRR
est. MRR
CourseNarrator
Auto-narrate e-learning slides and course scripts
$2K–$5K MRR
est. MRR
VoiceBot
Conversational voice interface for SaaS dashboards
$3K–$7K MRR
est. MRR

Parameters

textrequired
Text to synthesize — max 4096 characters· e.g. Welcome to APlicious. The developer API platform.
voiceoptional
alloy / echo / fable / onyx / nova / shimmer (default: nova)· e.g. nova
formatoptional
mp3 / opus / aac / flac / wav / pcm (default: mp3)· e.g. mp3
speedoptional
Speed multiplier 0.25–4.0 (default: 1.0)· e.g. 1.0

Example request

curl
curl -X POST https://aplicious.com/api/v1/tools/tts \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Welcome to APlicious.","voice":"nova","format":"mp3"}' \
  --output speech.mp3

Example response

json
# Returns audio binary (mp3)
# Response headers:
X-Voice: nova
X-Format: mp3
X-Processing-Ms: 1240
X-Estimated-Duration-Sec: 3.2
Content-Type: audio/mpeg
Ready to use Text to Speech?

Free plan — 100 calls/month, no credit card.