Text-to-Speech

# Stream audio as OpenAI speech events (SSE).
# Each "speech.audio.delta" carries a base64 PCM chunk; "speech.audio.done"
# ends the stream and declares the format and sample rate produced.
curl https://api.inferexai.in/v1/audio/speech \
  -H "Authorization: Bearer sk-live-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-voice",
    "input": "नमस्ते! मैं आपकी कैसे मदद कर सकता हूँ?",
    "voice": "ananya",
    "response_format": "pcm",
    "sample_rate": 24000,
    "stream_format": "sse"
  }'

# Voice-agent frameworks (pipecat, LiveKit) read raw PCM progressively —
# no special flag. Request a raw PCM format and read the body as a stream;
# audio arrives in ~milliseconds instead of after full synthesis.
response = client.audio.speech.create(
    model="tts-voice",
    voice="ananya",
    input="नमस्ते!",
    response_format="pcm",   # raw signed 16-bit PCM
    # response_format="mulaw" for an 8 kHz telephony (PSTN) leg
)
# response.iter_bytes() yields audio frames as they are produced

curl https://api.inferexai.in/v1/audio/speech \
  -H "Authorization: Bearer sk-live-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-voice",
    "input": "नमस्ते! मैं आपकी कैसे मदद कर सकता हूँ?",
    "voice": "ananya",
    "response_format": "mp3"
  }' \
  --output audio.mp3

from inferexai import InferexAI
from pathlib import Path

client = InferexAI(api_key="sk-live-your-key")

response = client.audio.speech.create(
    model="tts-voice",   # use a TTS model ID from /v1/models
    voice="ananya",
    input="नमस्ते! मैं आपकी कैसे मदद कर सकता हूँ?",
    response_format="mp3",
)

Path("output.mp3").write_bytes(response.content)

import InferexAI from "inferexai";
import fs from "fs";

const client = new InferexAI({ apiKey: "sk-live-your-key" });

const mp3 = await client.audio.speech.create({
  model: "tts-voice",
  voice: "ananya",
  input: "नमस्ते! मैं आपकी कैसे मदद कर सकता हूँ?",
  response_format: "mp3",
});

fs.writeFileSync("output.mp3", Buffer.from(await mp3.arrayBuffer()));

// Fetch + Web Audio API (browser / edge runtime)
const response = await fetch(
  "https://api.inferexai.in/v1/audio/speech",
  {
    method: "POST",
    headers: {
      "Authorization": "Bearer sk-live-your-key",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      model: "tts-voice",
      voice: "ananya",
      input: "Hello from the browser!",
      response_format: "mp3",
    }),
  }
);

const blob = await response.blob();
const url = URL.createObjectURL(blob);
const audio = new Audio(url);
audio.play();