Voice · Text to Speech
Text to Speech that speaks straight into your calls.
Turn text or SSML into natural neural speech that plays into a live call: IVR prompts, OTP read-outs, outbound alerts, and voice-bot replies. Voices in 30+ languages, on telephony in 50+ countries. No audio files to record or host. Ships on-premise for banking and healthcare where data cannot leave the firewall.
One line of text, spoken to the caller
Your application sends the words; EnableX synthesises and plays them on the live call. No pre-recorded prompts, no audio pipeline to maintain.
IVR menus and prompts
Welcome messages, menu options, error prompts, and confirmations are all synthesised from text at call time. Change the script and the next call hears the new version, no re-recording, no audio hosting.
OTP and verification read-outs
Pass the security code as SSML with character-by-character instructions so each digit is spoken clearly and individually. The same control handles account numbers, dates, and currency amounts.
Personalised alert calls
Outbound calls that include a customer's name, appointment time, or balance can't use static audio. TTS fills a template with runtime values and speaks the full message dynamically.
Voice-bot responses
In a live voice bot, TTS is the output half of the loop: your NLU or LLM layer writes the reply, and TTS speaks it back to the caller in real time for a fluid spoken conversation.
How it works
Configure a neural voice against your number in the Portal once. After that, any text your Play API sends is synthesised and played on the call.
Speak any text into a call
Place a call and pass the words in action_on_connect.play.text, EnableX synthesises and plays them through the neural voice. Copy, paste, run.
curl -X POST https://api.enablex.io/voice/v1/call \
-u APP_ID:APP_KEY \
-H "Content-Type: application/json" \
-d '{
"from": "+14155550100",
"to": "+442079460000",
"action_on_connect": {
"play": { "text": "Your OTP is 4 8 2 1 5 9. It is valid for ten minutes.", "language": "en-IN", "voice": "female" }
},
"event_url": "https://yourserver.com/webhook"
}'const axios = require('axios');
const res = await axios.post(
'https://api.enablex.io/voice/v1/call',
{
from: '+14155550100',
to: '+442079460000',
action_on_connect: {
play: { text: 'Your OTP is 4 8 2 1 5 9. It is valid for ten minutes.', language: 'en-IN', voice: 'female' }
},
event_url: 'https://yourserver.com/webhook'
},
{ auth: { username: 'APP_ID', password: 'APP_KEY' } }
);
console.log(res.data);import requests
from requests.auth import HTTPBasicAuth
res = requests.post(
"https://api.enablex.io/voice/v1/call",
auth=HTTPBasicAuth("APP_ID", "APP_KEY"),
json={
"from": "+14155550100",
"to": "+442079460000",
"action_on_connect": {
"play": {"text": "Your OTP is 4 8 2 1 5 9. It is valid for ten minutes.", "language": "en-IN", "voice": "female"}
},
"event_url": "https://yourserver.com/webhook"
}
)
print(res.json())Tuned for phone calls, not studio playback
A standalone TTS product hands you an audio clip. EnableX gives you speech that plays into the call, in the language your customer speaks, with the controls telephony needs.
Text and SSML
Send plain text for default rendering, or SSML for explicit control over pauses, reading speed, and emphasis on the words that matter.
Digit-by-digit read-out
SSML reads OTPs, reference numbers, and codes one character at a time, so the caller catches every digit the first time.
Neural voices, male and female
Choose the voice per phone number in the Portal. Natural-sounding output for prompts, alerts, and voice-bot replies.
Multilingual
30+ languages, including English, Hindi, Arabic, Bahasa Indonesia, Tamil, Telugu, Bengali, and Tagalog, matched to the markets EnableX Voice serves.
No audio pipeline
No recording studio, no file hosting, no format conversion, and no re-recording cycle. Updating what the caller hears is a text change.
On-prem for regulated buyers
Run the full voice stack, TTS included, inside your own data centre for BFSI, insurance, and healthcare deployments with data-residency rules.
Standalone TTS API: audio files on demand
A standalone service for synthesising reusable MP3 or WAV files from text is under development, for pre-building prompt libraries, batch campaign audio, and voice-over assets outside a live call. Register interest for early access.
Request early accessExplore EnableX AI-powered voice solutions
AI voice agent
Pair TTS with ASR and an LLM to deploy voice agents that hold human-like conversations across sales, support, and collections.
AI voice agentsVoice broadcasting
Run large-scale outbound campaigns with TTS-synthesised prompts that personalise each call, no pre-recorded audio.
Voice broadcastingAutomatic Speech Recognition
The input half of the voice loop: transcribe callers in real time in 30+ languages, then answer with TTS.
Speech recognition APIText to Speech FAQs
Build with Text to Speech: Developer Docs
See EnableX in action.
Talk to sales, or start a free trial. No credit card required.
Free trial credits · No credit card · API keys in 2 minutes