Beatra

Capabilities overview

Every Beatra capability in one matrix: modality, MCP tool, REST endpoint, execution mode.

One row per capability. Agents pick a tool here, then open the capability page for arguments, task status, and recovery. Models, controls, and prices are discovered live with beatra.models.list; to browse what's available right now, see the current model lineup.

Images

CapabilityInput → OutputMCP toolREST endpoint
Image understanding1–8 images + text → textbeatra.images.understandPOST /v1/images/responses
Text to imagetext → imagebeatra.images.generatePOST /v1/images/generations
Image to imageimage + text → imagebeatra.images.transformPOST /v1/images/image-to-image
Image editimage + text → imagebeatra.images.editPOST /v1/images/edits

Videos

CapabilityInput → OutputMCP toolREST endpoint
Video understandingone video + text → textbeatra.videos.understandPOST /v1/videos/responses
Video prompt enhancementtext + optional references → enhanced textbeatra.videos.enhance_promptPOST /v1/videos/prompts/enhance
Text to videotext → videobeatra.videos.generatePOST /v1/videos/text-to-video
Image to videoimage + text → videobeatra.videos.animatePOST /v1/videos/image-to-video
Reference to videoreferences + text → videobeatra.videos.generate_from_referencesPOST /v1/videos/reference-to-video
Frames to videorequired last frame + optional first frame + text → videobeatra.videos.interpolatePOST /v1/videos/frames-to-video
Video editvideo + references + text → videobeatra.videos.editPOST /v1/videos/edit
Video extendvideo + text → videobeatra.videos.extendPOST /v1/videos/extend

Speech & voices

CapabilityInput → OutputMCP toolREST endpoint
Text to speechtext + voice → audiobeatra.speech.synthesizePOST /v1/audio/speech
Voice cloneaudio sample → voicebeatra.voices.clonePOST /v1/voices
Voices— (management)beatra.voices.listGET /v1/voices

Music

CapabilityInput → OutputMCP toolREST endpoint
Text to musicprompt / lyrics → audiobeatra.music.generatePOST /v1/music/text-to-music
Reference audio to musicaudio + text → audiobeatra.music.generatePOST /v1/music/reference-audio-to-music

Public social data

CapabilityInput → OutputMCP toolREST endpoint
Public social datapublic social query → JSON (text, metrics, media URLs)beatra.social.tools.search / get / executeMCP only

Social reads reuse the existing OAuth MCP connection. Each execute is one prepaid task priced at 6, 12, 30, or 60 credits. There is no public Social REST API.

Shared contract

Every create or understanding call above is billable and returns an asynchronous task: 202 + a Task envelope, polled with beatra.tasks.get (or GET /v1/tasks/{task_id}) until terminal. Discovery and management reads (voices, models, tasks) are synchronous. The full lifecycle — envelope schema, cancellation, refunds — is defined once in Async tasks and applies to every row.

On this page