> ## Documentation Index > Fetch the complete documentation index at: https://docs.boson.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create a video (streaming) > Same request body as `POST /v1/videos`, but the response body IS the live fragmented-MP4 (fMP4) byte stream — frames arrive as they are generated, so playback can start before the clip is complete. The video id rides back in the `X-Video-Id` header; the full MP4 is stored too, so a later `GET /v1/videos/{video_id}/content` works. ## OpenAPI ````yaml /openapi.json post /v1/videos/stream openapi: 3.0.3 info: title: Boson AI API description: REST API for Boson AI audio models. version: 1.0.0 license: name: Proprietary servers: - url: https://api.boson.ai security: - bearerAuth: [] paths: /v1/videos/stream: post: tags: - Videos summary: Create a video (streaming) description: >- Same request body as `POST /v1/videos`, but the response body IS the live fragmented-MP4 (fMP4) byte stream — frames arrive as they are generated, so playback can start before the clip is complete. The video id rides back in the `X-Video-Id` header; the full MP4 is stored too, so a later `GET /v1/videos/{video_id}/content` works. operationId: streamVideo requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateVideoRequest' multipart/form-data: schema: type: object required: - ref_image properties: model: type: string default: higgs-avatar ref_image: type: string format: binary description: >- Reference image file (PNG/JPEG/WEBP), or an http(s) URL string. input: type: string format: binary description: >- Audio-to-video driving-audio file (AAC/WAV/MP3/FLAC/OPUS), or an http(s) URL string. Provide exactly one of `input` / `input_tts`. input_tts: type: string description: >- Text-to-video: a JSON string of a speech request. Provide exactly one of `input` / `input_tts`. size: type: string default: 640x640 responses: '200': description: The fragmented-MP4 (fMP4) byte stream. headers: X-Video-Id: schema: type: string description: The video id, for a later retrieve / download. content: video/mp4: schema: type: string format: binary '400': description: Invalid request (same codes as `POST /v1/videos`). content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate limited, or all replicas busy (`all_replicas_busy`). content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: CreateVideoRequest: type: object required: - ref_image additionalProperties: false description: >- Provide a `ref_image` plus exactly one driving input: `input` (audio-to-video) or `input_tts` (text-to-video). properties: model: type: string default: higgs-avatar enum: - higgs-avatar description: Avatar model ID / public alias. ref_image: type: string description: >- Reference image (the face to animate): an http(s) URL, data URI, or base64-encoded raw image bytes. Supported formats: PNG, JPEG, WEBP. Inline (base64 / data-URI) payloads: max 10 MB. input: type: string nullable: true description: >- Audio-to-video: the driving speech audio as an http(s) URL, data URI, or base64-encoded raw audio bytes. Supported formats: AAC, WAV, MP3, FLAC, OPUS. Max duration: 60 s (it sets the output video length). Provide exactly one of `input` / `input_tts`. input_tts: allOf: - $ref: '#/components/schemas/CreateSpeechRequest' nullable: true description: >- Text-to-video: a speech request (the same body as `POST /v1/audio/speech`). The gateway synthesizes the voice and the avatar lip-syncs to it. The nested `stream` field is not supported. Provide exactly one of `input` / `input_tts`. size: type: string enum: - 640x640 - 640x480 - 480x640 default: 640x640 description: >- Output video size (WxH): square `640x640`, landscape `640x480`, or portrait `480x640`. Error: type: object properties: error: type: object properties: message: type: string description: Human-readable error message. type: type: string description: Error category. CreateSpeechRequest: type: object required: - input additionalProperties: false properties: input: type: string minLength: 1 maxLength: 5000 description: >- Text to convert to speech. May contain inline tags. Inputs longer than 5000 characters return a 400 `input_too_long`. example: Hello, this is a test. model: type: string default: higgs-tts-3 enum: - higgs-tts-3 description: >- TTS model ID / public alias. Resolved to the served model server-side. voice: type: string default: default description: >- Preset voice name or custom voice ID. Mutually exclusive with `ref_audio` / `ref_text` when explicitly provided. response_format: type: string enum: - mp3 - opus - pcm - wav - aac - flac default: mp3 description: Output audio format. Streaming requires `pcm`. stream: type: boolean default: false description: >- If true, stream raw PCM chunks as they are decoded. Requires `response_format` to be `pcm`. Speed adjustment is not supported when streaming. ref_audio: type: string nullable: true description: >- Inline reference audio for one-off cloning: an http(s) URL, data URI, or base64-encoded raw audio bytes. Supported formats: AAC, WAV, MP3, FLAC, OPUS. Inline (base64 / data-URI) payloads: max 10 MB. ref_text: type: string nullable: true description: Recommended transcript of `ref_audio`. securitySchemes: bearerAuth: type: http scheme: bearer description: 'Your Boson API key, sent as `Authorization: Bearer $BOSON_API_KEY`.' ````