AI & machine learning

Machine learning: train models, run chat-based data exploration, and manage projects

Agent orchestration: distribute tasks, route agent messages, and manage sessions, skills and MCP servers

Translation: machine translation, translation memories, termbase lexicon, jobs, projects and file uploads

Computer vision: create projects, upload images, train and deploy image models

AI memory: store, query, and organize user memories, buckets and chat history

AI: ask a persona questions, list personas, browse models and their catalog

Voice AI agents: build agents, place calls, manage corpora, voices, SIP and telephony

Speech AI: transcribe media, generate TTS audio, run voice agents and call analytics

Web search, extraction, crawling, mapping and research for LLM agents

LLM access: chat, responses and messages endpoints, batch jobs and web search

Flows: run saved Runchat workflows, read their schema, edit canvases and transcribe audio

LLM access: chat, messages, image generation, plus account balance and API key management

AI agents, workspaces, tables and outreach campaigns: drive workers, read rows, manage sequences and senders

LLM gateway: chat, images, audio, video and agent tools via one OpenAI-compatible API

LLM gateway: chat, embeddings, image, audio, video and batch jobs via OpenAI-compatible endpoints

AI models: chat, image, video, speech and embeddings generation via one API

Arabic speech AI: text-to-speech in dialects, voice cloning, transcription, translation and Arabic diacritization

AI models: list models, generate and edit images, create and download videos

AI gateway: chat, image, embedding and model APIs, plus agents, workflows, knowledge bases and billing

LLM completions: chat, code fill-in-the-middle and code edits on Mercury models

Inference: run chat completions, list models, and check service health

Voice AI: text to speech, speech to text, and phone-based agents with tools and knowledge sources

AI agents: create and manage agents, rooms, memories, messaging, speech and audio, media uploads

AI models: chat, image and video generation, speech, embeddings, proxy keys and usage tracking