ElevenLabs

Voice specialist for speech synthesis plus transcription. Use it when you need natural-sounding narration from ElevenLabs voices, optionally with speech-to-text on the same key. The config key is eleven (not elevenlabs).

Capabilities

Audio generation and transcription.

Configuration

Configure via environment variables. config/ai.php only forwards them with env() — set the values in .env or the host environment, never hardcode keys in the config file.

// In config/ai.php
return [
    'Ai' => [
        'providers' => [
            'eleven' => [
                'className' => 'Crustum\Ai\Providers\ElevenLabsProvider',
                'key' => env('ELEVENLABS_API_KEY'),
                'url' => env('ELEVENLABS_URL', 'https://api.elevenlabs.io/v1'),
                'models' => [
                    'audio' => [
                        'default' => env('ELEVENLABS_AUDIO_MODEL', 'eleven_multilingual_v2'),
                    ],
                    'transcription' => [
                        'default' => env('ELEVENLABS_TRANSCRIPTION_MODEL', 'scribe_v2'),
                    ],
                ],
            ],
        ],
    ],
];

Config key	Env var	Purpose
className	—	Provider class. Keep the default unless subclassing.
key (apiKey also accepted)	ELEVENLABS_API_KEY	Key from elevenlabs.io. Required.
url	ELEVENLABS_URL	API base URL. Change only for proxies or gateways.
models.audio.default	ELEVENLABS_AUDIO_MODEL	Voice model for text-to-speech. Voice selection itself is a per-call option; this picks the synthesis engine.
models.transcription.default	ELEVENLABS_TRANSCRIPTION_MODEL	Speech-to-text (Scribe) model.
headers	— (config only)	Extra HTTP headers merged into every request. Add as a plain array if needed.

Per-call model: overrides the configured model for that call.

See also

• Providers — capability matrix
• Audio — speech and transcription