VUI Labs: Luna TTS (Text to Audio) API Reference

About

VUI Labs Luna TTS synthesizes Chinese, English, Japanese and Korean speech for voiceovers, narration and voice prompts, with system and cloned voices. Expression tags such as [laughs], [sighs] or [breath] go directly in the text. Infron serves it through the OpenAI-compatible POST /v1/audio/speech endpoint with wav or pcm output and optional streaming. A request takes up to 500 weighted characters and is billed per weighted character (a Chinese, Japanese or Korean character counts as 2).

1. Calling the API

Setup your API Key

To begin using Infron, create an account and generate your API Key.

export INFRON_KEY="YOUR_API_KEY"

Submit a request

Send JSON to POST https://llm.onerouter.pro/v1/audio/speech with your Infron API key. The request and response follow the OpenAI speech API, so the OpenAI SDKs work with the base URL https://llm.onerouter.pro/v1. The examples use the VUI Labs voice avery. Replace YOUR_API_KEY with your key.

curl

curl https://llm.onerouter.pro/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "vui/luna-tts/text-to-audio",
    "voice": "avery",
    "input": "Hello! Welcome to Infron.",
    "response_format": "wav"
  }' \
  --output speech.wav

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.onerouter.pro/v1",
    api_key="YOUR_API_KEY",
)

with client.audio.speech.with_streaming_response.create(
    model="vui/luna-tts/text-to-audio",
    voice="avery",
    input="Hello! Welcome to Infron.",
    response_format="wav",
) as response:
    response.stream_to_file("speech.wav")

TypeScript (OpenAI SDK)

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://llm.onerouter.pro/v1",
  apiKey: "YOUR_API_KEY",
});

const response = await client.audio.speech.create({
  model: "vui/luna-tts/text-to-audio",
  voice: "avery",
  input: "Hello! Welcome to Infron.",
  response_format: "wav",
});
fs.writeFileSync("speech.wav", Buffer.from(await response.arrayBuffer()));

Response

A successful request returns HTTP 200 with the audio file as the body, not JSON. Content-Type follows response_format: audio/wav for wav, audio/pcm for pcm. The examples above save it as speech.wav.

Streaming

Add "stream_format": "sse" to receive Server-Sent Events while the audio is generated. Each speech.audio.delta event carries the next base64 chunk of the audio in response_format; decode the chunks and append them in order. The stream ends with a speech.audio.done event that reports usage.

curl https://llm.onerouter.pro/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "vui/luna-tts/text-to-audio",
    "voice": "avery",
    "input": "Hello! Welcome to Infron.",
    "response_format": "wav",
    "stream_format": "sse"
  }' \
  --no-buffer
data: {"type":"speech.audio.delta","audio":"<base64 audio chunk>"}

data: {"type":"speech.audio.delta","audio":"<base64 audio chunk>"}

data: {"type":"speech.audio.done","usage":{"input_tokens":25,"output_tokens":0,"total_tokens":25}}

In this example input_tokens is the billable character count of the input.

Routing and usage

This model is served by vui (VUI Labs). Billing uses VUI's weighted character count (X-Luna-Billable-Characters): Chinese characters, Japanese kana and Korean Hangul count as 2, line breaks are not counted, other characters count as 1. The audio response carries no usage; with streaming, speech.audio.done reports the billable count as usage.input_tokens.

Errors

Parameters this model does not accept are rejected with HTTP 400 before the request is sent to VUI Labs, and nothing is charged. error.message explains the problem and ends with the request ID:

{
  "error": {
    "message": "voice is required (VUI voice_id) (request id: 20261111221810441285700pZnPkvCJ)",
    "type": "infron_ai_error",
    "param": "",
    "code": "invalid_request_error"
  }
}

Errors reported by VUI Labs, such as an unknown voice ID, are returned with VUI Labs's message. If a stream fails after it has started, an error event is sent instead of speech.audio.done.

2. Schema

Input

ParameterTypeRequiredDefaultRangeDescription
modelstringYes--vui/luna-tts/text-to-audioModel ID.
inputstringYes--Up to 500 weighted charactersText to synthesize; whitespace at both ends is trimmed. Expression tags: [laughs], [chuckles], [sighs], [inhales], [breath], [exhale], [gasps], [coughs], [clears throat], [sniffles], [snorts], [hisses], [tsks], [groans].
voicestringYes----VUI voice ID, for example avery. List voices for this model with VUI's List Voices API (model_id=luna-tts); cloned voices also work.
response_formatstringNowavwav, pcmAudio format. pcm is signed 16-bit little-endian without a header; read the sample rate and channels from the X-Audio-Sample-Rate, X-Audio-Channels and X-Audio-Bit-Depth response headers.
speednumberNo10.6 to 1.2Speaking rate.
languagestringNo--zh, en, ja, koLanguage of the text.
text_normalizationbooleanNotruetrue, falseNormalize the text before synthesis; false keeps the input as written.
stream_formatstringNoaudioaudio, ssesse streams Server-Sent Events (see Streaming).

VUI Labs fields

These fields are not part of the OpenAI speech API. Put them at the top level of the JSON body; with the OpenAI Python SDK pass them in extra_body.

ParameterTypeRequiredDefaultRangeDescription
volumenumberNo0-5 to 5 (dB, step 0.1)Volume adjustment. Applies to non-streaming requests only; omit it when streaming.

Unsupported fields

FieldBehavior
instructions, sample_rate, bit_rateIgnored.
Other fieldsNot forwarded to VUI Labs.

Output

ParameterTypeRangeDescription
Response bodybinarywav, pcmThe audio file in response_format (without stream_format=sse).
Content-Type headerstringaudio/wav, audio/pcmMIME type of the audio.
X-Audio-Sample-Rate, X-Audio-Channels, X-Audio-Bit-Depth headersinteger--Sample rate, channel count and bit depth of pcm output.
typestringspeech.audio.delta, speech.audio.done, errorStreaming event type.
audiostringBase64Next chunk of the audio (speech.audio.delta).
usage.input_tokensintegerNon-negativeBillable count of the input (speech.audio.done).
usage.output_tokensinteger0Always 0 for this model.
usage.total_tokensintegerNon-negativeSum of input and output.
errorobject--message, type and code of a failure (error event).

3. Detailed Pricing

ModelEndpointBilling unitPrice
VUI Labs: Luna TTSvuiPer 1M weighted characters$15.00

Prices are in USD. Billing uses VUI's weighted character count (X-Luna-Billable-Characters): Chinese characters, Japanese kana and Korean Hangul count as 2, line breaks are not counted, other characters count as 1.

Sources: Text to speech API, Luna TTS, List voices, Pricing.