canonical: https://jentic.com/apis/audiomap.ai/audiomap # AudioMap API The AudioMap API transcribes audio and video, then lets you read, analyse, and query the result programmatically. It imports media from a public link or a direct upload, returns transcripts with segments, speaker labels, and word timings, and can translate them into other languages. From a transcript it generates analyses, chapter outlines, question answers over one or all notes, and written deliverables. ## For AI agents Transcribe audio and video, read transcripts with speakers and timings, translate them, and ask questions across recordings. Returns structured JSON over a bearer-authenticated REST API. ## Scope Does not host live calls, generate speech from text, or edit the source media. Use for transcribing, analysing, and querying recorded audio and video only. ## Capabilities - Transcribe audio and video from a public link or a direct upload - Return transcripts with segments, speaker labels, and word timings - Translate a transcript into another language - Generate analysis templates and chapter outlines for a note - Answer questions about one note or across every note you own - Write documents and deliverables from a note's content ## Use cases ### AI Agent Transcription Integration via Jentic An agent that works with recordings can call AudioMap through Jentic without wiring the bearer key or managing the upload-and-poll flow. The agent searches by intent, receives the operation schema, imports or uploads media, and reads the transcript back as structured JSON. This fits meeting assistants, media pipelines, and research tools that turn speech into text they can act on. Example prompt: Search Jentic for 'transcribe an audio file', load the operation schema, import the recording, and read back the transcript ### Audio and Video Transcription Turn a recording into text with segments, speaker labels, and word-level timings. AudioMap accepts a public link or a direct upload, processes it, and returns a transcript an agent can parse, caption, or index. Translation into another language is available on the same transcript. Example prompt: Call POST `/v1/notes` to import a recording, then GET `/v1/notes/{id}/transcript` to read the transcript ### Transcript Q&A and Search Ask natural-language questions about a single recording or across every recording you own, with answers grounded in the transcripts rather than invented. This lets a research or support agent pull a specific fact from one call, or find which recordings mention a topic across a library. Example prompt: Call POST `/v1/notes/{id}/ask` with a question to get an answer grounded in one note's transcript ### Deliverable Generation from Recordings Produce written outputs such as summaries or structured documents directly from a note's content. An agent can generate a meeting recap or an analysis template from a transcript, then list the deliverables created for that note for follow-up. Example prompt: Call POST `/v1/notes/{noteId}/deliverables` to write a summary document from a note ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/notes` | Import from a link or open a direct upload | | GET | `/v1/notes` | List notes, newest first | | GET | `/v1/notes/{id}/transcript` | Get the transcript with segments and speakers | | POST | `/v1/notes/{id}/transcript/translation` | Translate the transcript into a language | | POST | `/v1/notes/{id}/analysis` | Generate or regenerate an analysis template | | POST | `/v1/notes/{id}/ask` | Ask a question about one note | | POST | `/v1/ask` | Ask a question across every note you own | | POST | `/v1/notes/{noteId}/deliverables` | Write a document from the note | ## Key resources - **Notes** — Import, upload, list, and read recordings and their text - **Transcripts** — Segments, speakers, word timings, and translations - **Analysis** — Analysis templates and chapter outlines for a note - **Ask** — Question answering over one note or every note - **Deliverables** — Documents written from a note's content ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 65 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 82 / 100 - Developer Experience & Jentic Compatibility: 66 / 100 - AI-Readiness & Agent Experience: 48 / 100 - Agent Usability: 94 / 100 - Security: 60 / 100 - AI Discoverability: 63 / 100 - **View full report:** https://jentic.com/apis/audiomap.ai/audiomap/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the AudioMap API by hand means managing its bearer key, uploading or importing media, polling until processing finishes, and shaping transcript, analysis, and ask requests yourself. Through Jentic you install once, import AudioMap from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** AudioMap puts the note id in the URL path (`/v1/notes/{id}/...`), so a rule can pin your agent to the note operations you pick. You choose the operations it may call, so you can allow transcript reads and questions while leaving new uploads and translation writes out. - **Credential handling:** Your AudioMap API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'transcribe a recording' or 'ask about a note', and Jentic returns the matching AudioMap operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Deepgram API** — Alternative speech-to-text with streaming and batch transcription - **Rev AI** — Alternative asynchronous speech-to-text transcription - **ElevenLabs API** — Text-to-speech voice synthesis ## FAQ ### Is there an AudioMap MCP server? You don't need a separate MCP server to give your agent the AudioMap API. Jentic connects it directly from the API Directory: import it, store your bearer key once, and your agent calls the transcription, translation, and ask operations it needs. ### Can I limit what my agent is allowed to do with the AudioMap API? Yes. Write a rule that allows reading a note's transcript and asking questions about it under one note id, so the agent can read and query that recording while importing new media or starting a translation stays out of reach. Every call is logged by your self-hosted instance. ### What authentication does the AudioMap API use? The AudioMap API authenticates with a bearer API key sent in the Authorization header, per its OpenAPI spec. A session JWT is not accepted; the REST API expects an API key. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time. ### Can I ask questions about a recording with the AudioMap API? Yes. After a note is transcribed you can ask a question about that single note, or ask across every note you own, and AudioMap answers grounded in the transcripts. It also generates analyses, outlines, and written deliverables from the same content. ### What are the rate limits for the AudioMap API? The OpenAPI spec does not specify rate limits, though the REST API is available from the Pro plan up and a lower-plan call returns a 403 with the required tier. Check the vendor's documentation at https://audiomap.ai for current limits and plan tiers. ### How do I transcribe a recording with the AudioMap API through Jentic? Search Jentic for 'transcribe an audio file' and it returns the AudioMap import operation with its input schema; supply a link or upload and the agent reads the transcript back as structured JSON. To run it on your own infrastructure, install Jentic One from its GitHub repo.