Register a reusable voice from a base voice and optional delivery instructions. This synchronous request returns the audio resource ID in data.id. Save that ID and pass the exact same value in input.audio_ids when creating a character or calling Gemini Omni Flash 1.1 Reference to Video.
Developer API pricing
Provider: SeeAPI
USD estimate: $0.0037 / credit · Estimated equivalent, not an additional charge.
Price: 0 credits/gen (≈ $0.00/gen)
/v1/generationsA stable key for each resource creation request. Reuse it only when retrying the identical request.
create-audio-001The model ID shown in the selected model's API documentation.
gemini-omni-audiogemini-omni-audiogemini-omni-audioCreate Audio. Use the Endpoint ID shown in this model's API documentation.
create-audiocreate-audiocreate-audioOptional public Provider ID. Omit it to use the Endpoint default Provider (seeapi).
seeapiseeapiseeapiCreation parameters for the selected resource endpoint and public Provider.
Provider parameters
seeapiDefault ProviderBase voice identifier. This is different from the reusable audio resource ID returned after creation.
achernarachirdalgenibalgiebaalnilamaoedeautonoecallirrhoecharondespinaenceladuserinomefenrirgacruxiapetuskorelaomedeialedaoruspuckpulcherrimarasalgethisadachbiasadaltagerschedarsulafatumbrielvindemiatrixzephyrzubenelgenubikoreDisplay name for the registered voice.
AriOptional instructions for tone, pacing, articulation, and intended use.
A bright, clear voice with natural pacing, crisp articulation, and subtle enthusiasm.Optional sample line that illustrates the desired speaking style.
Let me show you a simple idea that makes everyday life easier.The created resource. The same request and Idempotency-Key return the saved resource directly.
The audio resource ID returned by this creation request. Save it and pass the exact returned value as an item in input.audio_ids when creating a character or generating a video with Gemini Omni Flash 1.1 / reference-to-video.
Resource type.
audioResource name.
An optional image preview URL, not an audio playback URL. Newly created audio resources may return null.
Saved public creation details.
The base voice used to register this voice.
Saved voice delivery instructions, when provided.
Saved example dialogue, when provided.
Invalid JSON, parameters, Schema, or API Policy
Invalid API Key or authentication failed
The current request is not allowed
Model, Endpoint, or referenced resource not found
Idempotency conflict, or creation could not be confirmed. Retry the identical request with the same key; do not create a duplicate.
Request body is too large
Too many requests
Service temporarily unavailable
const response = await fetch("https://api.seeapi.com/v1/generations", {
method: "POST",
headers: {
"Authorization": "Bearer YOUR_API_KEY",
"Idempotency-Key": "create-audio-001",
"Content-Type": "application/json"
},
body: JSON.stringify({
"model": "gemini-omni-audio",
"endpoint": "create-audio",
"provider": "seeapi",
"input": {
"audio_id": "kore",
"name": "Ari",
"voice_description": "A bright, clear voice with natural pacing, crisp articulation, and subtle enthusiasm.",
"example_dialogue": "Let me show you a simple idea that makes everyday life easier."
}
})
});
const result = await response.json();{
"data": {
"id": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
"type": "audio",
"name": "Ari",
"preview_url": null,
"details": {
"basic_voice": "kore",
"voice_description": "Warm, clear delivery at a relaxed conversational pace.",
"example_dialogue": "Let us discover something new together."
}
}
}