Manage video subtitles, captions, and translations on the Amara platform. Add and manage videos from YouTube, Vimeo, or direct URLs. Create, upload, download, and edit subtitles in multiple formats (DFXP, SRT, VTT, SSA, SBV) across any supported language. Perform subtitle workflow actions including saving drafts, publishing, approving, and rejecting. Add notes to subtitle sets for collaborator communication. Manage teams with configurable membership policies and role-based access control. Organize videos into projects, handle team membership applications, and configure team language preferences. Track and manage multi-stage subtitle requests with assignees and due dates across collaborating teams. View activity logs for videos, teams, and users. Create and manage user accounts, send messages to users or teams, and retrieve supported languages.

Transcribe pre-recorded and live audio/video to text with support for 99+ languages, speaker diarization, and multichannel audio. Apply audio intelligence models to extract summaries, sentiment analysis, entity detection, topic detection, key phrases, and content moderation from transcripts. Redact personally identifiable information from text and audio. Generate SRT/VTT subtitles and segment transcripts into paragraphs, sentences, or auto-chapters. Stream real-time speech-to-text via WebSocket connections. Upload audio/video files for processing. Manage and delete transcripts. Access an LLM gateway to apply large language models (Claude, GPT, Gemini) to transcribed speech data for summarization, Q&A, and custom analysis. Translate transcripts across 99+ languages. Receive webhook notifications when transcriptions complete or fail.

Generate text and chat completions using Cohere's Command family of large language models, with support for multi-turn conversations, retrieval augmented generation (RAG), tool use, reasoning, vision, structured output, and translation. Create text and image embeddings for semantic search, classification, and clustering. Rerank search results by semantic relevance. Transcribe speech audio. Manage batch embedding jobs and datasets for large-scale document processing. Tokenize and detokenize text for cost estimation. List available models and their capabilities.