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.

Transcribe audio to text using real-time, fast, or batch transcription modes with speaker diarization and language identification. Convert text to synthesized speech using neural, custom, or personal voices with SSML control over pronunciation and prosody. Generate photorealistic avatar videos from text. Translate speech across multiple languages. Verify and identify speakers by voice characteristics. Assess pronunciation accuracy, fluency, completeness, and prosody for language learning. Supports custom speech models trained on domain-specific data and LLM-enhanced transcription for captions, meeting summaries, and call center assistance.

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, and translation. Create text and image embeddings for semantic search, classification, and clustering. Rerank search results by semantic relevance. Manage batch embedding jobs and datasets for large-scale document processing. Tokenize and detokenize text for cost estimation. List available models and their capabilities.

Manage localization projects, upload source files, and coordinate multilingual translations. Create and organize translation projects (file-based or string-based), upload and manage source files and strings, add and download translations, and build translation exports. Manage translation memories, glossaries, and machine translation engines. Configure AI providers and prompts for translation workflows. Create and assign translation or proofreading tasks with deadlines and progress tracking. Upload screenshots and tag them with source strings for translator context. Generate reports on translation progress, costs, and contributor productivity. Invite and manage team members with role-based access. Retrieve translation and approval status at project, file, language, or branch level. Distribute translations via over-the-air CDN distributions. Receive webhooks for file, project, string, translation, task, and comment events. Crowdin Enterprise additionally supports workflow management, organization groups, vendors, and teams.

Look up word definitions, phonetics, pronunciations, synonyms, antonyms, and example sentences. Retrieve detailed linguistic information for words across multiple languages, including parts of speech, IPA transcriptions, and audio pronunciation URLs. Supports querying in any available language by language code.

Extract meaning from text and voice inputs using natural language processing. Detect intents, entities, and traits from text messages with confidence scores. Transcribe and analyze audio files and streams via speech recognition. Synthesize human-like speech from text. Manage multi-turn conversational flows with dialogue state and context. Detect languages from text input. Create, update, and delete entities, intents, and training utterances programmatically. Manage Wit.ai apps, export and import app configurations, and train NLU models with annotated samples.

Convert text to lifelike speech with customizable voices, intonation, and emotional awareness across 70+ languages. Transcribe speech to text with real-time streaming or batch processing. Clone, generate, and manage voices. Generate music, sound effects, and multi-speaker dialogue from text descriptions. Dub and translate audio/video content into other languages. Deploy and manage conversational voice agents with phone integration, knowledge bases, and analytics. Isolate vocals from background noise, align text to audio timestamps, and remix voice characteristics. Manage pronunciation dictionaries, access generation history, and retrieve usage statistics. Supports webhook notifications for call completions, transcription results, and voice events.

Transcribe audio and video files to text using asynchronous or real-time streaming modes. Supports 100+ languages with automatic language detection and code-switching. Perform speaker diarization to identify different speakers. Translate transcripts into multiple target languages. Generate summaries, sentiment analysis, named entity recognition, and chapter segmentation from audio. Extract structured data and produce subtitles in SRT/VTT formats. Apply custom vocabulary and spelling corrections, content moderation, and name consistency. Send custom prompts to generate LLM-powered responses from transcripts. Receive results via polling, callback URLs, or account-level webhooks.

Transcribe, subtitle, and translate audio and video files using AI-powered or human professional services. Upload media files, create transcription and subtitling orders in 120+ languages, translate transcriptions into 70+ target languages, and export results in multiple formats (TXT, DOCX, PDF, SRT, VTT, STL, XML, JSON, and more). Manage transcriptions with folders, tags, glossaries, and style guides. Configure webhooks for order status notifications.

Analyze unstructured and semi-structured text using natural language processing across Asian, European, and Middle Eastern languages. Extract entities (persons, locations, organizations, products) and link them to knowledge bases like Wikidata and DBpedia. Determine sentiment at document or entity level. Compare and match names across languages accounting for transliterations, nicknames, and spelling variations. Translate names between 13+ languages. Deduplicate name lists across scripts. Compare address and record similarity. Extract relationships and events connecting entities. Categorize documents by topic using IAB taxonomy. Discover keyphrases and concepts via topic extraction. Perform morphological analysis including part-of-speech tagging, lemmatization, and compound decomposition. Tokenize text, detect sentences, identify languages (55 supported), compute semantic similarity via text embeddings, parse syntactic dependencies, and transliterate text between scripts.

Analyze text to detect abusive content (hate speech, cyberbullying, sexual harassment, criminal activity), extract sentiment, named entities, and topics across 30+ languages. Detect languages in text fragments, calculate semantic similarity between texts, compare named entities cross-linguistically, translate text between supported languages, and clean up markup from text. Provides low-level NLP capabilities including tokenization, part-of-speech tagging, and morphological analysis. Supports configurable content moderation with severity scoring and explanations, document-level and expression-level sentiment analysis, and direct access to underlying language model entries.

Convert text to lifelike speech audio with customizable AI voices, models, languages, and output formats. Transcribe speech to text in real-time or batch mode. Manage, clone, and design voices from audio samples or text prompts. Generate music and sound effects from text descriptions. Dub and translate audio/video content into other languages. Isolate vocals from background noise, change voices in audio, and generate multi-speaker dialogue. Create and manage conversational AI agents with knowledge bases and tool integrations. Manage studio projects for long-form audio productions like audiobooks. Configure pronunciation dictionaries and administer workspace settings, users, and usage analytics.

Smartling MCP Server

Lingo.dev MCP Server - World-class i18n implementation with ICU MessageFormat.

A Model Context Protocol (MCP) Server for Lara Translate API, enabling powerful translation capabilities with support for language detection and context-aware translations.

Connect to Lara Translate API, enabling powerful translation capabilities with support for langua...