Audio

Atlas provides three focused audio modalities — speech, music, and sound effects — each with a dedicated API.

Speech (TTS & STT)

Convert text to speech or transcribe audio to text:

use Atlasphp\Atlas\Atlas;

$response = Atlas::speech('openai', 'tts-1')
    ->instructions('Hello, welcome to Atlas!')
    ->withVoice('alloy')
    ->asAudio();

→ Full documentation

Music

Generate music from text prompts:

$response = Atlas::music('elevenlabs')
    ->instructions('An upbeat jazz piano track')
    ->withDuration(30)
    ->asAudio();

→ Full documentation

Sound Effects

Generate sound effects from text descriptions:

$response = Atlas::sfx('elevenlabs')
    ->instructions('Thunder with heavy rain')
    ->withDuration(5)
    ->asAudio();

→ Full documentation

Low-Level API

Atlas::audio() is the underlying entry point that all three modalities build on. Use it directly for advanced use cases or future audio capabilities:

$response = Atlas::audio('openai', 'tts-1')
    ->instructions('Direct audio API usage')
    ->withVoice('alloy')
    ->asAudio();

Supported Providers

Provider	TTS	STT	SFX	Music	Features
OpenAI	tts-1, tts-1-hd	whisper-1	—	—	Voices, speed, format
ElevenLabs	eleven_multilingual_v2	Yes	eleven_text_to_sound_v2	Yes	Voices, cloning, languages, SFX, music
xAI	grok-2-audio	—	—	—	TTS

Storing Audio

$response->store('public');
$response->storeAs('audio/greeting.mp3', 'public');

Automatic Storage

When persistence is enabled, generated audio is automatically stored to disk and tracked as an Asset record — no manual store() call needed. See each sub-page or Media & Assets for details.

Persisted Asset

When persistence is enabled, generated audio is automatically stored to disk:

if ($response->asset) {
    $response->asset->path;       // Storage path
    $response->asset->mime_type;  // "audio/mpeg"
    $response->asset->disk;       // Filesystem disk
}

See Media & Assets for the complete storage guide.

Queue Support

All audio modalities support queue dispatch:

Atlas::speech('openai', 'tts-1')
    ->instructions('Generate a long audiobook chapter')
    ->withVoice('nova')
    ->queue()
    ->asAudio()
    ->then(fn ($response) => $response->store('public'));

See Speech, Music, and Sound Effects for modality-specific queue examples.

AudioResponse

Property	Type	Description
data	string	Raw audio binary data
format	?string	Audio format (mp3, wav, etc.)
meta	array	Additional metadata
asset	?Asset	Linked asset (when persistence enabled)