--- title: AssemblyAI API Integration on Truto slug: assemblyai category: Conversational Intelligence canonical: "https://truto.one/integrations/detail/assemblyai/" --- # AssemblyAI API Integration on Truto **Category:** Conversational Intelligence **Status:** Generally available ## MCP-ready AI tools Truto exposes 14 tools for AssemblyAI that AI agents can call directly. - **create_a_assembly_ai_upload** — Upload a media file to AssemblyAI's servers as raw binary data. Returns the uploaded file object upon success, which can be referenced in subsequent transcription requests. - **list_all_assembly_ai_transcripts** — List AssemblyAI transcripts sorted from newest to oldest. Returns: id, status, audio_url. Transcripts are available for the last 90 days of usage. - **create_a_assembly_ai_transcript** — Create an AssemblyAI transcript from a media file accessible via URL. Returns the transcript object including id and status; processing is asynchronous—poll via get until status is "completed". Required: audio_url. - **get_single_assembly_ai_transcript_by_id** — Get an AssemblyAI transcript by id. Returns the transcript resource including id, status, text, and audio_url; the transcript is ready when status is "completed". Required: id. - **delete_a_assembly_ai_transcript_by_id** — Delete an AssemblyAI transcript by id, removing all associated data and marking it as deleted. Returns the deleted transcript object. Required: id. - **list_all_assembly_ai_sentences** — Get the sentences for an AssemblyAI transcript, semantically segmented for reader-friendly output. Returns an array of sentence objects. Required: transcript_id. - **list_all_assembly_ai_paragraphs** — Get the paragraphs of an AssemblyAI transcript, semantically segmented for reader-friendly output. Returns an array of paragraph objects. Required: transcript_id. - **list_all_assembly_ai_word_searches** — Search an AssemblyAI transcript for keywords or phrases and return all matching occurrences. Returns: matches. Required: transcript_id, words. Each search term can be an individual word, number, or phrase of up to five words. - **list_all_assembly_ai_redacted_audios** — Get the redacted audio in AssemblyAI for a specific transcript using transcript_id. Returns status indicating redacted audio readiness and redacted_audio_url containing the downloadable file link. Redacted audio is available for 24 hours only. - **get_single_assembly_ai_subtitle_by_id** — Get subtitles for an AssemblyAI transcript in the specified format. Returns the subtitle file content for the given transcript. Required: id, subtitle_format. - **create_a_assembly_ai_chat_completion** — Create a chat completion in AssemblyAI. Generates model responses based on provided messages or prompt. Returns choices array with message content, finish_reason, and usage details for token counts. - **create_a_assembly_ai_speech_understanding** — Create a speech understanding task in AssemblyAI for a given transcript_id. Performs translation, speaker_identification, or custom_formatting on the transcript. Returns response objects with task status, mappings, formatted_text, and translated_texts. - **list_all_assembly_ai_streaming_token** — Generate a temporary streaming_token in AssemblyAI. Requires expires_in_seconds parameter. Returns token and expires_in_seconds fields, which indicate the generated temporary authentication token and its redemption window. - **list_all_assembly_ai_voice_agent_token** — Generate a temporary Voice Agent token in AssemblyAI. Requires expires_in_seconds. Returns token and expires_in_seconds fields used to authenticate a single session. ## How it works 1. **Link your customer's AssemblyAI account.** Use Truto's frontend SDK; we handle every OAuth and API key flow so you don't need to create the OAuth app. 2. **Authentication is automatic.** Truto refreshes tokens, stores credentials securely, and injects them into every API request. 3. **Call Truto's API to reach AssemblyAI.** The Proxy API is a 1-to-1 mapping of the AssemblyAI API. 4. **Get a unified response format.** Every response uses a single shape, with cursor-based pagination and data in the `result` field. ## Use cases - **Add AI-powered call intelligence to sales platforms** — Sales enablement and CRM SaaS companies can let their users connect AssemblyAI to automatically transcribe and analyze customer calls. Truto handles the auth and async transcription flow so teams ship Gong-style features in days, not quarters. - **Embed compliant transcription in healthcare and legal SaaS** — Telehealth, EHR, and LegalTech platforms can offer their customers PII-redacted transcripts and audio for HIPAA-sensitive workflows. End users bring their own AssemblyAI account, and the SaaS app delivers automated SOAP notes or deposition transcripts without owning the compliance burden. - **Power interactive video and podcast experiences for media platforms** — Video editing suites, podcast hosts, and EdTech platforms can give creators auto-generated subtitles, paragraph-level transcripts, and word-level search inside their player. Truto exposes the segmentation and subtitle endpoints behind one consistent interface. - **Ship live agent assist for contact center SaaS** — CCaaS and UCaaS platforms can offer real-time transcription and AI co-pilot features by issuing short-lived streaming tokens to the agent's browser. The SaaS owns the UX while AssemblyAI handles the live STT. - **Layer generative AI workflows on top of recorded conversations** — Any SaaS sitting on a library of recorded audio can let customers run custom LLM prompts against their transcripts — extracting action items, scoring calls, or generating summaries — using AssemblyAI's chat completion endpoint instead of routing through a separate LLM provider. ## What you can build - **End-to-end async transcription pipeline** — Upload media files to AssemblyAI, kick off a transcript job, and fetch the completed result through a single integration layer. - **Interactive transcript viewer with timestamps** — Render readable transcripts segmented by sentences and paragraphs with millisecond timestamps for clickable, jump-to-moment playback. - **Auto-generated SRT/VTT subtitles for video** — Pull standard subtitle formats directly from a transcript ID so customers can publish captioned video without a separate captioning tool. - **In-video word search and navigation** — Let end users search for keywords inside long recordings and jump to the exact timestamp where each match occurs. - **AI call scorecards and summaries** — Send custom prompts against a transcript to extract objections, grade reps, or generate structured summaries — all without a separate LLM integration. - **PII-redacted audio storage for compliance** — Offer customers a redacted audio file with sensitive information beeped out, ready to attach to a patient record, case file, or call log. ## FAQs ### How does end-user authentication to AssemblyAI work? AssemblyAI uses API key authentication. Through Truto's connected account flow, your end users provide their AssemblyAI API key once, and Truto securely stores and injects it on every API call your product makes on their behalf. ### Is transcription synchronous or asynchronous? AssemblyAI's transcription API is asynchronous. You call create_a_assembly_ai_transcript to start a job, then either poll get_single_assembly_ai_transcript_by_id until the status is 'completed' or rely on AssemblyAI's webhook to notify your service. ### How do I upload media files for transcription? Use create_a_assembly_ai_upload to send the raw audio or video binary to AssemblyAI's storage. The response returns an upload URL that you then pass to create_a_assembly_ai_transcript to begin processing. ### Can I support real-time streaming transcription from the browser? Yes. Use list_all_assembly_ai_streaming_token or list_all_assembly_ai_voice_agent_token to mint short-lived tokens server-side, then hand them to your frontend so the client can stream audio directly to AssemblyAI without exposing the user's long-lived API key. ### How do I get readable transcripts instead of one large block of text? Once a transcript is completed, call list_all_assembly_ai_sentences or list_all_assembly_ai_paragraphs to retrieve semantically segmented chunks with timestamps. For video captions, use get_single_assembly_ai_subtitle_by_id to fetch SRT or VTT output. ### How long are redacted audio files available? Redacted audio files generated via list_all_assembly_ai_redacted_audios are available for 24 hours from AssemblyAI. If your product needs long-term retention, download the file within that window and persist it in your own storage. ## Related reading - [Connect AssemblyAI to Claude: Process Speech and Generate Subtitles](https://truto.one/blog/connect-assemblyai-to-claude-process-speech-and-generate-subtitles/) — Learn how to connect AssemblyAI to Claude using a managed MCP server. Automate asynchronous transcription, subtitle generation, and speech analysis. - [Connect AssemblyAI to ChatGPT: Transcribe and Analyze Audio Content](https://truto.one/blog/connect-assemblyai-to-chatgpt-transcribe-and-analyze-audio-content/) — Learn how to connect AssemblyAI to ChatGPT using a managed MCP server. Execute async transcriptions, process binary uploads, and run AI audio workflows. - [Connect AssemblyAI to AI Agents: Automate Voice Data Workflows](https://truto.one/blog/connect-assemblyai-to-ai-agents-search-and-understand-voice-data/) — Learn how to connect AssemblyAI to AI agents using Truto. Fetch AI-ready tools, handle async transcripts, and execute multi-step voice data workflows.