Create Generation

curl -X POST "https://api.audixa.ai/v3/tts" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "text": "Hello from Audixa. This request is long enough for generation.",
    "voice_id": "am_ethan",
    "model": "base",
    "speed": 1.0,
    "audio_format": "wav",
    "language_code": "a"
  }'

import requests

response = requests.post(
    "https://api.audixa.ai/v3/tts",
    headers={"X-API-Key": "YOUR_API_KEY"},
    json={
        "text": "Hello from Audixa. This request is long enough for generation.",
        "voice_id": "am_ethan",
        "model": "base",
        "audio_format": "wav",
    },
    timeout=30,
)
response.raise_for_status()
generation = response.json()
print(generation["generation_id"], generation["status"])

const response = await fetch('https://api.audixa.ai/v3/tts', {
  method: 'POST',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    text: 'Hello from Audixa. This request is long enough for generation.',
    voice_id: 'am_ethan',
    model: 'base',
    audio_format: 'wav'
  })
});
if (!response.ok) throw new Error(await response.text());
const generation = await response.json();
console.log(generation.generation_id, generation.status);

{
  "generation_id": "gen_abc123xyz",
  "status": "IN_QUEUE",
  "input_text": "Hello from Audixa. This request is long enough for generation.",
  "voice_id": "am_ethan",
  "voice_name": "Ethan",
  "model": "base",
  "tokens": 6,
  "dollar_cost": 0.000006,
  "method": null,
  "created_at": "2025-02-05T12:00:00Z",
  "started_at": null,
  "completed_at": null
}

POST

tts

curl -X POST "https://api.audixa.ai/v3/tts" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "text": "Hello from Audixa. This request is long enough for generation.",
    "voice_id": "am_ethan",
    "model": "base",
    "speed": 1.0,
    "audio_format": "wav",
    "language_code": "a"
  }'

import requests

response = requests.post(
    "https://api.audixa.ai/v3/tts",
    headers={"X-API-Key": "YOUR_API_KEY"},
    json={
        "text": "Hello from Audixa. This request is long enough for generation.",
        "voice_id": "am_ethan",
        "model": "base",
        "audio_format": "wav",
    },
    timeout=30,
)
response.raise_for_status()
generation = response.json()
print(generation["generation_id"], generation["status"])

const response = await fetch('https://api.audixa.ai/v3/tts', {
  method: 'POST',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    text: 'Hello from Audixa. This request is long enough for generation.',
    voice_id: 'am_ethan',
    model: 'base',
    audio_format: 'wav'
  })
});
if (!response.ok) throw new Error(await response.text());
const generation = await response.json();
console.log(generation.generation_id, generation.status);

{
  "generation_id": "gen_abc123xyz",
  "status": "IN_QUEUE",
  "input_text": "Hello from Audixa. This request is long enough for generation.",
  "voice_id": "am_ethan",
  "voice_name": "Ethan",
  "model": "base",
  "tokens": 6,
  "dollar_cost": 0.000006,
  "method": null,
  "created_at": "2025-02-05T12:00:00Z",
  "started_at": null,
  "completed_at": null
}

Submits a text-to-speech task and returns a generation_id for tracking. The audio is generated asynchronously—use the Get Generation endpoint to check when it’s ready.

Endpoint

POST https://api.audixa.ai/v3/tts

Request

string

required

The text to convert to speech. At least 1 character is required. Each generation is billed for at least 30 characters (8 tokens), even for shorter text. The maximum is set by the active plan and cannot exceed the API schema maximum of 50,000 characters.

string

required

The voice ID to use. Get available voices from /voices.

string

default:"base"

The model tier to use.

base: Supports speed and Base-compatible voices.
advanced: Supports cfg_weight, exaggeration, and Advanced-compatible voices.

number

default:"1.0"

Playback speed multiplier. Range: 0.5 to 2.0.

Advanced Model Settings

number

default:"2.5"

Controls how strictly the model follows the text/style. Range: 1.0 - 5.0.

number

default:"0.5"

Controls emotional fluctuation/expressiveness. Range: 0.0 - 1.0.

string

default:"wav"

Output format: wav or mp3.

string

Optional language code for the input text. The accepted values depend on model:

Base model uses single-letter codes: a (American English), b (British English), j (Japanese), z (Mandarin Chinese), e (Spanish), f (French), h (Hindi), i (Italian), p (Brazilian Portuguese).
Advanced model uses ISO 639-1 codes: en, ar, da, de, el, es, fi, fr, he, hi, it, ja, ko, ms, nl, no, pl, pt, ru, sv, sw, tr, zh.

If omitted, the model falls back to its default language.

Response

string

Unique identifier for this generation job. Use this to poll /tts.

string

Initial status: IN_QUEUE.

string

The input text that was submitted.

string

Voice ID used for generation.

string

Human-readable voice name.

string

TTS model used (base or advanced).

integer

Number of tokens consumed.

number

Server-calculated cost in USD for the accepted generation.

string

Payment method used: API_WALLET or CREDITS_BALANCE.

string

URL to download the generated audio (when status=COMPLETED).

string

Error details if status=FAILED.

string

ISO 8601 timestamp of creation.

string

ISO 8601 timestamp when processing started.

string

ISO 8601 timestamp when processing completed.

curl -X POST "https://api.audixa.ai/v3/tts" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "text": "Hello from Audixa. This request is long enough for generation.",
    "voice_id": "am_ethan",
    "model": "base",
    "speed": 1.0,
    "audio_format": "wav",
    "language_code": "a"
  }'

import requests

response = requests.post(
    "https://api.audixa.ai/v3/tts",
    headers={"X-API-Key": "YOUR_API_KEY"},
    json={
        "text": "Hello from Audixa. This request is long enough for generation.",
        "voice_id": "am_ethan",
        "model": "base",
        "audio_format": "wav",
    },
    timeout=30,
)
response.raise_for_status()
generation = response.json()
print(generation["generation_id"], generation["status"])

const response = await fetch('https://api.audixa.ai/v3/tts', {
  method: 'POST',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    text: 'Hello from Audixa. This request is long enough for generation.',
    voice_id: 'am_ethan',
    model: 'base',
    audio_format: 'wav'
  })
});
if (!response.ok) throw new Error(await response.text());
const generation = await response.json();
console.log(generation.generation_id, generation.status);

{
  "generation_id": "gen_abc123xyz",
  "status": "IN_QUEUE",
  "input_text": "Hello from Audixa. This request is long enough for generation.",
  "voice_id": "am_ethan",
  "voice_name": "Ethan",
  "model": "base",
  "tokens": 6,
  "dollar_cost": 0.000006,
  "method": null,
  "created_at": "2025-02-05T12:00:00Z",
  "started_at": null,
  "completed_at": null
}

Error Responses

400 Bad Request

Invalid parameters (e.g. invalid model, voice not found).

402 Payment Required

Insufficient balance.

429 Too Many Requests

Rate limit exceeded.

Overview

Endpoints

Streaming

Request

Advanced Model Settings

Response

Error Responses

​Request

​Advanced Model Settings

​Response

​Error Responses

Request

Advanced Model Settings

Response

Error Responses