# Streaming summaries Streaming summaries combine file transcription and summarization in a multipart HTTP request. The response contains Server-Sent Events (SSE), including the completed transcript and summary text as it is generated. ## Submit a recording Use this endpoint: **`POST /aiservices/speech-summarization/summarize`** Authenticate with your [Zoom AI Services credentials](/docs/ai-services/auth/). The examples on this page send a token in the `Authorization: Bearer` header. | Form field | Required | Description | | ---------- | -------- | ---------------------------------------------------------------------------------- | | `file` | Yes | One audio or video file uploaded as binary data. | | `config` | No | JSON string containing `transcribe` and `summary` settings. Send it before `file`. | This example uploads a project-update recording and selects the corresponding static summary template: ```shell curl --no-buffer --fail-with-body \ https://api.zoom.us/v2/aiservices/speech-summarization/summarize \ -H "Authorization: Bearer $TOKEN" \ -H "Accept: text/event-stream" \ -F 'config={"transcribe":{"language":"en-US","diarization":false,"profanity_filter":false},"summary":{"language":"en-US","template_id":"project_update","enable_dynamic_template":false,"citations":true,"should_remove_sentiment":false}}' \ -F 'file=@project-update.wav;type=audio/wav' ``` Add the `config` part before the `file` part. Let your HTTP client set the multipart `Content-Type` header and boundary. In cURL, `-F` does this automatically. `--no-buffer` displays events as they arrive. Keep credentials on a trusted backend. Read the POST response as a stream with your HTTP client; a browser's native `EventSource` cannot submit this multipart POST request. ## Configure transcription Put recognition settings in `config.transcribe`. The recognition model is selected automatically and can't be changed. | Field | Type | Default | Description | | ------------------ | ------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `language` | string | `en-US` | Input speech locale. Supports the ten languages listed under [Multilingual model languages](/docs/ai-services/scribe/speech-understanding/#multilingual-model-languages). | | `diarization` | boolean | `false` | Identify different speakers in the recording. | | `profanity_filter` | boolean | `false` | Filter profanity in the transcript. | For accepted media formats and upload limits, see [Recording requirements](/docs/ai-services/speech-summarization/#recording-requirements). ## Configure summarization Put summary settings in `config.summary`. The summary language can differ from the transcription language. | Field | Type | Default | Description | | ------------------------- | ------- | ------- | --------------------------------------------------------------------------------------------------------- | | `language` | string | `en-US` | Summary output language. | | `template_id` | string | None | Predefined summary template. See [Static templates](#static-templates). | | `custom_template` | string | None | A Markdown template. The summary follows its headings, structure, and formatting. | | `summary_length` | string | `short` | `short` or `long`. | | `citations` | boolean | `true` | Include references to transcript evidence in the summary. | | `should_remove_sentiment` | boolean | `false` | Remove most sentiment and emotion expressions from the summary. Removal isn't guaranteed to be complete. | | `enable_dynamic_template` | boolean | `true` | Automatically select a template based on the meeting type when no static or custom template is specified. | ### Automatic template Omit `template_id` and `custom_template` and set `enable_dynamic_template` to `true`, or leave it at its default. The API detects the meeting type and selects a template. ```json { "summary": { "language": "en-US", "enable_dynamic_template": true, "citations": true } } ``` ### Static templates Set `template_id` to one of these values. Selecting a static template disables automatic template selection. You can also set `enable_dynamic_template` to `false` explicitly. | Template ID | Purpose | | ------------------ | --------------------------- | | `one_on_one` | One-on-one meeting | | `stand_up` | Stand-up meeting | | `brainstorm` | Brainstorming session | | `project_update` | Project update | | `discussion` | General discussion | | `q_a` | Question-and-answer session | | `customer_success` | Customer success call | | `user_feedback` | User feedback session | | `lecture_summary` | Lecture summary | | `next_steps` | Next steps and action items | ### Custom template Set `custom_template` to a Markdown template. The summary follows the template's headings, structure, and formatting. A custom template overrides automatic template selection. Choose one template mode per request. ```json { "summary": { "language": "en-US", "custom_template": "## Decisions\n- \n\n## Owners\n| Person | Task |\n| --- | --- |\n", "enable_dynamic_template": false, "citations": false } } ``` ## Handle the event stream A successful streaming response uses `Content-Type: text/event-stream`. Each event has an `event:` name and JSON in its `data:` field. A blank line separates events. HTTP response chunks do not necessarily align with SSE event boundaries. Buffer incomplete events before parsing their JSON. | Event | Meaning | Client action | | --------------------- | ------------------------------------- | ---------------------------------------------------------------------------- | | `transcribe_started` | Transcription has started. | Show transcription progress. | | `transcribe_complete` | The complete transcript is available. | Save `transcript` for display or downstream use. | | `summary_updated` | The summary has been updated. | Replace the displayed summary with `summary_result`. Check `response_state`. | | `done` | Processing completed. | Save the last summary and mark the request complete. | | `error` | A processing stage failed. | Handle the error and retain any completed transcript. | ### Transcription events ```text event: transcribe_started data: {"status":"transcribing"} event: transcribe_complete data: {"transcript":{"request_id":"3f2b8c1e-7a4d-4e9b-b6f0-1c5d8a2e9b47","duration_sec":5.2,"result":{"text_display":"We agreed to release the documentation on October fifteenth.","segments":[{"id":"utt_0000","start":0.0,"end":5.2,"channel":0,"speaker":"","text":"We agreed to release the documentation on October fifteenth.","words":[]}]}},"latency_ms":5234,"body_bytes":12456,"status_code":200} ``` `transcribe_complete` includes the transcription result in `transcript`, the transcription latency in `latency_ms`, the size of the transcription result in `body_bytes`, and the transcription status in `status_code`. The example shows a shortened transcript; it is not a complete list of response fields. ### Summary updates Each `summary_updated` event contains the full summary so far in `summary_result`. Replace the displayed text with each update. `response_state` is `working` during generation and `completed` in the final update. Skip empty `summary_result` values when updating the display. HTML in the summary is escaped: `
` arrives as `<br>`. ```text event: summary_updated data: {"summary_result":"## Decisions\n- Release the documentation on October fifteenth.","citations":null,"response_state":"working","error":null} event: summary_updated data: {"summary_result":"## Decisions\n- Release the documentation on October fifteenth.[^1]","response_state":"completed","error":null,"citations":[{"id":1,"marker":"[^1]","start_time":"00:00:00.000","end_time":"00:00:05.200","start_item_index":0,"end_item_index":0}]} ``` The summary is Markdown. When `citations` is enabled, the final update adds Markdown footnote markers, such as `[^1]`, and a `citations` array that links each marker to the transcript. Earlier updates have `"citations": null`. | Field | Description | | ------------------------------------ | ------------------------------------------------------------------------------------------------------------- | | `id` | Citation number. | | `marker` | The marker used in the summary text, such as `[^1]`. | | `chunk_id` | ID of the transcript chunk that supports the statement. | | `speaker` | Speaker label of the cited chunk. | | `start_time`, `end_time` | The cited span of the recording, in `HH:MM:SS.mmm` format. Use them to find the matching transcript segments. | | `start_item_index`, `end_item_index` | The first and last transcript segments in the cited span. | Preserve the markers when displaying or storing the summary. ### Completion ```text event: done data: {"status":"complete","total_latency_ms":8500,"transcribe_ms":5234,"summary_ms":3266} ``` The `done` event reports total processing latency and the transcription and summary stage latencies, in milliseconds. Save the last `summary_result`; the `done` payload does not repeat the summary text. ## Handle errors Check the HTTP status, then read the SSE events. HTTP `200` starts the stream. A successful request ends with a `summary_updated` event with `response_state: "completed"`, followed by `done`. Treat an `error` event, a `summary_updated` event with `response_state: "error"`, or a connection that ends before `done` as a failure. When processing fails, the API sends an `error` event without `done`. | HTTP status | Meaning | | ------------- | ----------------------------------------------------------------------- | | `200` | Streaming response. Read events to determine the outcome. | | `400` | Invalid configuration, missing file, or unsupported format. | | `401` / `403` | Invalid credentials, or the request isn't authorized. | | `402` | Your credit is exhausted, or the credential's credit limit was reached. | | `405` | Incorrect HTTP method; use POST. | | `413` | Upload exceeds 50 MB. | | `429` | Too many requests. See [rate limits](/docs/api/rate-limits/). | | `502` | Transcription or summary service error. | | `503` | The summary service is temporarily unavailable. | An SSE error identifies the failed stage: ```text event: error data: {"error":"transcribe failed: connection timeout","stage":"transcribe"} ``` | Stage | Meaning | | --------------------- | -------------------------------------------------- | | `transcribe` | Transcription failed. | | `summary_preparation` | Preparing the transcript for summarization failed. | | `summary` | Summary generation failed. | If transcription fails, the API does not return a partial transcript. If summary generation fails after `transcribe_complete`, retain the completed transcript and show that summarization did not finish.