Beyond text, through the same API
The Amanai dashboard and API now support image creation and editing, video, speech, realtime audio, and vectors alongside the existing chat and Responses endpoints.
What's live
Image generation & editing
Prompt, one source image for edits, and model-specific aspect ratio, resolution, and quality controls.
Video generation
Durable text-to-video and image-to-video jobs with progress polling and downloadable output.
Speech synthesis
Text-to-speech with Eve, language hints, and MP3 or WAV output.
Speech transcription
Speech-to-text with supported language hints and JSON, text, or verbose JSON output.
Realtime voice
WebRTC conversations with instruction-based language control and voice selection.
Embeddings
Batch vector generation for search, retrieval, and semantic matching.
Owner-scoped files
Private uploads for image editing, image-to-video, and audio transcription.
Dashboard Playground
A single workspace for chat, media, realtime, and vectors.
Models
Each endpoint accepts a model ID for its modality. The authenticated model catalog is the source of truth for the image, video, speech, realtime, and vector models currently available to your key.
Get started
Use the same base URL and Bearer key as your current integration. The model below is an example; choose any compatible model returned by the authenticated catalog.
curl https://api.amanai.dev/v1/images/generations \
-H "Authorization: Bearer $AMANAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "amanai/grok-imagine-image-2.0",
"prompt": "A quiet coastal observatory at blue hour",
"aspect_ratio": "16:9",
"resolution": "1k"
}'Open the dashboard Playground to explore each modality, or read the dedicated Media and Realtime guides for endpoint contracts.