> ## Documentation Index > Fetch the complete documentation index at: https://heygen-1fa696a7.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Stream Avatar Realtime Word Timestamps > Open a Server-Sent Events (`text/event-stream`) stream of per-word timestamps for a session. Each `data:` frame is a `WordBatch` (`{"words": [{"word", "start", "end"}, ...]}`); times are in seconds from the start of the streamed audio (matching OpenAI Whisper and ElevenLabs). Punctuation is emitted as its own word event. Batches are capped at ~1s of audio or 10 words, whichever comes first. Late subscribers receive the full session history; completed sessions are served from a durable snapshot. The stream ends with a single `event: end` frame carrying a `WordsEndEvent`. ## OpenAPI ````yaml /openapi/external-api.json get /v3/avatar-realtime/{stream_id}/words openapi: 3.1.0 info: title: HeyGen External API version: 1.0.0 description: >- HeyGen's external API for programmatic AI video creation. See https://docs.heygen.com for full documentation. contact: name: HeyGen Product Infra url: https://heygen.com servers: - url: https://api.heygen.com description: Production security: - ApiKeyAuth: [] - BearerAuth: [] tags: - name: Video Agent description: Create videos from text prompts using AI - name: Videos description: Create, list, retrieve, and delete videos - name: Voices description: Text-to-speech and voice management - name: Audio description: Search the background-music and sound-effects catalog - name: Video Translate description: Translate videos into other languages - name: User description: Account information and billing - name: Avatars description: List and manage avatars and looks - name: Avatar Realtime description: >- Low-latency streaming avatar sessions — create a stream, poll for its HLS URL, push text, consume per-word timestamps - name: Assets description: Upload files for use in video creation - name: Webhooks description: Manage webhook endpoints and events - name: Lipsync description: Dub or replace audio on existing videos - name: Brand description: >- Brand-related resources — brand kits (colors, fonts, logos) and brand glossaries (custom term translations) - name: HyperFrames description: Render HyperFrames composition zips into video — separate from /v3/videos - name: AI Clipping description: Turn long-form videos into ready-to-share short clips with captions paths: /v3/avatar-realtime/{stream_id}/words: get: tags: - Avatar Realtime summary: Stream Avatar Realtime Word Timestamps description: >- Open a Server-Sent Events (`text/event-stream`) stream of per-word timestamps for a session. Each `data:` frame is a `WordBatch` (`{"words": [{"word", "start", "end"}, ...]}`); times are in seconds from the start of the streamed audio (matching OpenAI Whisper and ElevenLabs). Punctuation is emitted as its own word event. Batches are capped at ~1s of audio or 10 words, whichever comes first. Late subscribers receive the full session history; completed sessions are served from a durable snapshot. The stream ends with a single `event: end` frame carrying a `WordsEndEvent`. operationId: streamAvatarRealtimeWords parameters: - name: stream_id in: path required: true schema: type: string description: Streaming session identifier returned by POST /v3/avatar-realtime. responses: '200': description: >- Server-Sent Events stream (`text/event-stream`). Each `data:` frame carries one `WordBatch` JSON payload; the stream terminates with a single `event: end` frame whose data is a `WordsEndEvent`. content: text/event-stream: schema: $ref: '#/components/schemas/WordBatch' '400': description: Invalid request parameters content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' '401': description: Authentication failed content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: authentication_failed message: Invalid or expired API key. Verify your x-api-key header. param: null doc_url: null '404': description: Resource not found content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: not_found message: Streaming session not found. param: null doc_url: null '429': description: Rate limit exceeded content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: rate_limit_exceeded message: >- Too many requests. Retry after the duration specified in the Retry-After header. param: null doc_url: null headers: Retry-After: description: Seconds to wait before retrying schema: type: integer security: - ApiKeyAuth: [] - BearerAuth: [] components: schemas: WordBatch: description: One SSE `data:` payload — a batch of words that share a ~1s window. properties: words: description: Words in this batch, ordered by start time. items: $ref: '#/components/schemas/WordEvent' title: Words type: array required: - words title: WordBatch type: object StandardAPIError: type: object properties: code: type: string description: Machine-readable error code example: invalid_parameter message: type: string description: Human-readable error message example: Video not found param: type: - string - 'null' description: Which request field caused the error doc_url: type: - string - 'null' description: Link to error documentation required: - code - message WordEvent: description: |- One spoken word and its time bounds in the streamed audio. Punctuation (periods, commas, etc.) is emitted as its own event with its own time bounds — clients that don't care can filter them out. Times are in seconds, matching OpenAI Whisper and ElevenLabs alignment APIs. properties: word: description: >- The spoken token. May be a word, partial word, or a punctuation mark. title: Word type: string start: description: >- Word start time in seconds, measured from the beginning of the streamed audio. title: Start type: number end: description: >- Word end time in seconds, measured from the beginning of the streamed audio. title: End type: number required: - word - start - end title: WordEvent type: object securitySchemes: ApiKeyAuth: type: apiKey in: header name: x-api-key description: HeyGen API key. Obtain from your HeyGen dashboard. BearerAuth: type: http scheme: bearer description: OAuth2 bearer token. ````