Voice Synthesis

Audio Automation API

Generate voiceovers, podcast narration, and branded audio from any script. Powered by ElevenLabs — 40+ voices, 29 languages, SSML-style pacing control. Your audio is uploaded to the CDN and returned as a permanent URL.

Requires a paid plan. Get your API key at 1frx.com/dashboard.html

How it works

Request

Endpoint: POST /api/audio

Requires: X-1FRX-Key header

Parameters

Parameter Type Description
script string, required Text to synthesise, max 5,000 characters
voice_id string, optional ElevenLabs voice ID (default: Rachel — 21m00Tcm4TlvDq8ikWAM)
model string, optional eleven_multilingual_v2 (default), eleven_monolingual_v1, eleven_turbo_v2
stability number, optional 0–1, voice consistency (default: 0.5)
similarity number, optional 0–1, voice clarity (default: 0.75)
style number, optional 0–1, expressiveness v2 only (default: 0)
format string, optional "mp3" (default), "wav", "opus", "aac"

Example request

curl -X POST https://api.1frx.com/v1/audio \
  -H "X-1FRX-Key: sk_live_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "Welcome to the 1FRX platform. Build faster with AI-powered automation.",
    "voice_id": "21m00Tcm4TlvDq8ikWAM",
    "model": "eleven_multilingual_v2",
    "stability": 0.5,
    "similarity": 0.75,
    "format": "mp3"
  }'

Response

{
  "success": true,
  "url": "https://assets.1frx.com/audio/a3f9b2c1.mp3",
  "voice_id": "21m00Tcm4TlvDq8ikWAM",
  "model": "eleven_multilingual_v2",
  "format": "mp3",
  "characters": 78,
  "duration_est": 6.2,
  "size_bytes": 124832
}

Popular voices

Voice ID Description
Rachel 21m00Tcm4TlvDq8ikWAM Clear, professional, neutral American English
Adam pNInz6obpgDQGcFmaJgB Deep, narrative, British English
Bella EXAVITQu4vr4xnSDxMaL Warm, expressive, American English
Antoni ErXwobaYiN019PkySvjV Well-rounded, American English
Elli MF3mGyEYCl7XYWbV9V6O Emotional, American English

Supported output formats

Character limits by plan

What's next

OCR & Parse API Screenshot API API Reference