{ "tools": [ { "name": "check_credits", "scope": "account:read", "description": "Read the shared wallet balance in credits. Call before paid operations.", "inputSchema": { "type": "object", "properties": {}, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "check_capacity", "scope": "account:read", "description": "Read available concurrency slots and the remaining monthly budget of this credential. Call before create_conversation or send_message.", "inputSchema": { "type": "object", "properties": {}, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "list_conversations", "scope": "video_agents:read", "description": "List owned video conversations, newest first. status is one of queued, running, stopping, paused, completed, failed, stopped; next_action tells what a paused conversation needs. Times are Unix seconds.", "inputSchema": { "type": "object", "properties": { "limit": { "type": "integer", "minimum": 1, "maximum": 100, "description": "Items per page. Default 20." }, "offset": { "type": "integer", "minimum": 0, "description": "Items to skip. Default 0." } }, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "get_conversation", "scope": "video_agents:read", "description": "Read one conversation summary with status, next_action, cost_credits and preview_video_url. Use list_messages for per-message detail.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." } }, "required": [ "conversation_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "create_conversation", "scope": "video_agents:write", "description": "Create a video conversation and start the first paid message immediately. Check credits and capacity first. Outline modes: by default (require_outline_confirmation omitted or false) the video is generated straight through without pausing. With require_outline_confirmation=true the message pauses with status=paused and next_action=confirm_outline; show the returned outline to the user, then call send_message with outline_action=confirm (no prompt needed) or outline_action=revise plus a prompt describing the change. Poll list_messages every 5 seconds or more; there is no streaming. Billing matches the app: the platform reserve is held, released at the end, then actual usage is charged (clamped to the balance). cost_credits is the held reserve until the message settles, then the actual charge.", "inputSchema": { "type": "object", "properties": { "prompt": { "type": "string", "minLength": 1, "maxLength": 20000, "description": "The lesson or video brief: audience, goal, then # title and ## sections with concrete facts, numbers, formulas, dates or ordered steps. Do not name visual components." }, "idempotency_key": { "type": "string", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$", "description": "Retry key for this conversation. Generate a UUID once and reuse it only when retrying the same input; a different input with the same key is rejected. Never ask the user for it." }, "require_outline_confirmation": { "type": "boolean", "description": "Default false (generate straight through). Set true only when the user wants to review the outline first." }, "video_config": { "type": "object", "description": "Video settings applied when the conversation is created. They cannot be changed by send_message.", "properties": { "target_language": { "type": "string", "pattern": "^[A-Za-z]{2,3}([-_][A-Za-z0-9]{2,8})*$", "description": "Narration and subtitle language as an ISO 639-1 code or BCP-47 tag, for example en, zh or zh-CN. Default en. Decide before creating; changing it later means a new video." }, "video_duration": { "type": "string", "enum": [ "short", "deep", "long" ], "description": "short: 1–3 minutes (default). deep: 3–10 minutes. long: 10–20 minutes." }, "video_style": { "type": "string", "enum": [ "auto", "clean_lecture", "science_explainer", "professional_training", "product_showcase", "cinematic_story" ], "description": "auto (default) lets the agent choose. clean_lecture: courses. science_explainer: science processes. professional_training: workplace training. product_showcase: product demos. cinematic_story: history and narrative." }, "voice_id": { "type": "string", "description": "Narration voice id from list_voices. Default picks a voice for target_language." }, "voice_version": { "type": "integer", "enum": [ 1, 2 ], "description": "Version of voice_id: 1 (Voice I, default) or 2. Requires voice_id." }, "locale": { "type": "string", "description": "Optional native locale of voice_id, for example en-US. Requires voice_id." }, "avatar_id": { "type": [ "string", "integer" ], "description": "Presenter avatar id from list_avatars. The avatar must have selectable=true; otherwise create fails with avatar_not_ready." }, "brand_kit_id": { "type": [ "string", "integer" ], "description": "Brand kit id from list_brand_kits for colors, logo and tone." }, "enable_initial_ai_video": { "type": "boolean", "description": "Generate an AI opening clip when the plan allows it. Default false." } }, "additionalProperties": false }, "files": { "type": "array", "maxItems": 5, "description": "Up to 5 attachments. Each item uses an owned asset_id or a caller-supplied public http(s) URL. Third-party URLs are archived to the caller’s storage before use.", "items": { "type": "object", "description": "An attachment with asset_id or a public url and its own role.", "properties": { "asset_id": { "type": [ "string", "integer" ], "description": "id returned by POST /v1/assets or list_assets." }, "url": { "type": "string", "pattern": "^https?://", "description": "Caller-supplied public http(s) URL. Third-party content is archived before use." }, "name": { "type": "string", "maxLength": 255, "description": "Optional display name; inferred from the source when omitted." }, "type": { "type": "string", "enum": [ "document", "image", "video" ], "description": "Optional; inferred from the file when omitted." }, "files_role": { "type": "string", "enum": [ "primary", "reference" ], "description": "How this file shapes the video: primary or reference. Omit to let the agent decide." } }, "additionalProperties": false } }, "callback_url": { "type": "string", "maxLength": 2048, "description": "Optional public HTTPS URL notified once when this message reaches completed, paused, failed or stopped. Signed with the workspace callback secret (X-XPilot-Signature). Only set it when the user runs a receiving service." }, "callback_id": { "type": "string", "pattern": "^[\\w.:-]{1,128}$", "description": "Optional reference echoed back as data.callback_id. Requires callback_url." } }, "required": [ "prompt", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "send_message", "scope": "video_agents:write", "description": "Send a follow-up turn to a conversation that is not running. Paid. Use it to edit the video, answer the assistant (next_action=reply), or confirm/revise the outline (next_action=confirm_outline). Outline modes: by default (require_outline_confirmation omitted or false) the video is generated straight through without pausing. With require_outline_confirmation=true the message pauses with status=paused and next_action=confirm_outline; show the returned outline to the user, then call send_message with outline_action=confirm (no prompt needed) or outline_action=revise plus a prompt describing the change. video_config cannot be changed here.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." }, "prompt": { "type": "string", "maxLength": 20000, "description": "The instruction or answer. Required unless outline_action=confirm." }, "outline_action": { "type": "string", "enum": [ "confirm", "revise" ], "description": "Only when next_action=confirm_outline. confirm continues with the outline; revise needs a prompt describing the change." }, "idempotency_key": { "type": "string", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$", "description": "Retry key for this message. Generate a UUID once and reuse it only when retrying the same input; a different input with the same key is rejected. Never ask the user for it." }, "files": { "type": "array", "maxItems": 5, "description": "Up to 5 attachments. Each item uses an owned asset_id or a caller-supplied public http(s) URL. Third-party URLs are archived to the caller’s storage before use.", "items": { "type": "object", "description": "An attachment with asset_id or a public url and its own role.", "properties": { "asset_id": { "type": [ "string", "integer" ], "description": "id returned by POST /v1/assets or list_assets." }, "url": { "type": "string", "pattern": "^https?://", "description": "Caller-supplied public http(s) URL. Third-party content is archived before use." }, "name": { "type": "string", "maxLength": 255, "description": "Optional display name; inferred from the source when omitted." }, "type": { "type": "string", "enum": [ "document", "image", "video" ], "description": "Optional; inferred from the file when omitted." }, "files_role": { "type": "string", "enum": [ "primary", "reference" ], "description": "How this file shapes the video: primary or reference. Omit to let the agent decide." } }, "additionalProperties": false } }, "callback_url": { "type": "string", "maxLength": 2048, "description": "Optional public HTTPS URL notified once when this message reaches completed, paused, failed or stopped. Signed with the workspace callback secret (X-XPilot-Signature). Only set it when the user runs a receiving service." }, "callback_id": { "type": "string", "pattern": "^[\\w.:-]{1,128}$", "description": "Optional reference echoed back as data.callback_id. Requires callback_url." } }, "required": [ "conversation_id", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "list_messages", "scope": "video_agents:read", "description": "List messages of a conversation in order. Poll this for status, next_action, outline (when an outline exists), cost_credits and preview_video_url. completed, paused, failed and stopped are terminal for that message.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." } }, "required": [ "conversation_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "stop_conversation", "scope": "video_agents:write", "description": "Stop the running message. Poll list_messages until it is stopped; cost already incurred may still be charged.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." } }, "required": [ "conversation_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": true, "idempotentHint": true, "openWorldHint": false } }, { "name": "delete_conversation", "scope": "video_agents:write", "description": "Delete an owned conversation and stop any running message. Only when the user asks.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." } }, "required": [ "conversation_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": true, "idempotentHint": true, "openWorldHint": false } }, { "name": "list_renders", "scope": "video_agents:read", "description": "List MP4 exports of a conversation. status is queued, running, completed, failed or superseded. progress is a 0–100 percentage when known, otherwise null.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." } }, "required": [ "conversation_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "create_render", "scope": "video_agents:write", "description": "Export an MP4 after preview_video_url is available. A preview is not an export. Poll get_render and report its 0–100 progress until completed, then return video_url.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." }, "message_id": { "type": "string", "minLength": 1, "description": "Message to export. Default: the latest message with a preview." }, "force": { "type": "boolean", "description": "Re-export even when a completed export exists. Default false." }, "idempotency_key": { "type": "string", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$", "description": "Retry key for this export. Generate a UUID once and reuse it only when retrying the same input; a different input with the same key is rejected. Never ask the user for it." } }, "required": [ "conversation_id", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "get_render", "scope": "video_agents:read", "description": "Read one export: status, progress (0–100 or null when unavailable), and video_url when completed.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." }, "render_id": { "type": "string", "minLength": 1, "description": "render_id returned by create_render or list_renders." } }, "required": [ "conversation_id", "render_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "delete_render", "scope": "video_agents:write", "description": "Delete an export record. Only when the user asks.", "inputSchema": { "type": "object", "properties": { "conversation_id": { "type": "string", "minLength": 1, "description": "conversation_id returned by create_conversation or list_conversations." }, "render_id": { "type": "string", "minLength": 1, "description": "render_id returned by create_render or list_renders." } }, "required": [ "conversation_id", "render_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": true, "idempotentHint": true, "openWorldHint": false } }, { "name": "list_brand_kits", "scope": "brand_kits:read", "description": "List owned brand kits. Pass an id as video_config.brand_kit_id.", "inputSchema": { "type": "object", "properties": { "limit": { "type": "integer", "minimum": 1, "maximum": 100, "description": "Items per page. Default 20." }, "offset": { "type": "integer", "minimum": 0, "description": "Items to skip. Default 0." } }, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "get_brand_kit", "scope": "brand_kits:read", "description": "Read one owned brand kit.", "inputSchema": { "type": "object", "properties": { "brand_kit_id": { "type": [ "string", "integer" ], "description": "Brand kit id returned by list_brand_kits or create_brand_kit." } }, "required": [ "brand_kit_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "create_brand_kit", "scope": "brand_kits:write", "description": "Create a brand kit for logos, theme colors and tone. Only when the user asks.", "inputSchema": { "type": "object", "properties": { "brand_name": { "type": "string", "minLength": 1, "maxLength": 120, "description": "Brand name shown in videos." }, "brand_logo": { "type": "string", "maxLength": 2048, "description": "Logo URL, preferably one returned by POST /v1/assets." }, "content_style_description": { "type": "string", "maxLength": 20000, "description": "Tone and style guidance for scripts, for example \"friendly, concise, avoid jargon\"." }, "theme_color": { "type": "object", "description": "Theme colors. Each value is #rgb, #rrggbb, #rrggbbaa or rgb()/rgba(); null clears a color.", "properties": { "primary": { "type": [ "string", "null" ], "maxLength": 50, "description": "primary color." }, "secondary": { "type": [ "string", "null" ], "maxLength": 50, "description": "secondary color." }, "accent": { "type": [ "string", "null" ], "maxLength": 50, "description": "accent color." }, "background": { "type": [ "string", "null" ], "maxLength": 50, "description": "background color." }, "text": { "type": [ "string", "null" ], "maxLength": 50, "description": "text color." }, "textSecondary": { "type": [ "string", "null" ], "maxLength": 50, "description": "textSecondary color." }, "success": { "type": [ "string", "null" ], "maxLength": 50, "description": "success color." }, "warning": { "type": [ "string", "null" ], "maxLength": 50, "description": "warning color." }, "error": { "type": [ "string", "null" ], "maxLength": 50, "description": "error color." }, "surface": { "type": [ "string", "null" ], "maxLength": 50, "description": "surface color." }, "surfaceLight": { "type": [ "string", "null" ], "maxLength": 50, "description": "surfaceLight color." }, "shadow": { "type": [ "string", "null" ], "maxLength": 50, "description": "shadow color." } }, "additionalProperties": false } }, "required": [ "brand_name" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": false, "openWorldHint": false } }, { "name": "update_brand_kit", "scope": "brand_kits:write", "description": "Update fields of an owned brand kit. Omitted fields stay unchanged.", "inputSchema": { "type": "object", "properties": { "brand_kit_id": { "type": [ "string", "integer" ], "description": "Brand kit id returned by list_brand_kits or create_brand_kit." }, "brand_name": { "type": "string", "minLength": 1, "maxLength": 120, "description": "Brand name shown in videos." }, "brand_logo": { "type": "string", "maxLength": 2048, "description": "Logo URL, preferably one returned by POST /v1/assets." }, "content_style_description": { "type": "string", "maxLength": 20000, "description": "Tone and style guidance for scripts, for example \"friendly, concise, avoid jargon\"." }, "theme_color": { "type": "object", "description": "Theme colors. Each value is #rgb, #rrggbb, #rrggbbaa or rgb()/rgba(); null clears a color.", "properties": { "primary": { "type": [ "string", "null" ], "maxLength": 50, "description": "primary color." }, "secondary": { "type": [ "string", "null" ], "maxLength": 50, "description": "secondary color." }, "accent": { "type": [ "string", "null" ], "maxLength": 50, "description": "accent color." }, "background": { "type": [ "string", "null" ], "maxLength": 50, "description": "background color." }, "text": { "type": [ "string", "null" ], "maxLength": 50, "description": "text color." }, "textSecondary": { "type": [ "string", "null" ], "maxLength": 50, "description": "textSecondary color." }, "success": { "type": [ "string", "null" ], "maxLength": 50, "description": "success color." }, "warning": { "type": [ "string", "null" ], "maxLength": 50, "description": "warning color." }, "error": { "type": [ "string", "null" ], "maxLength": 50, "description": "error color." }, "surface": { "type": [ "string", "null" ], "maxLength": 50, "description": "surface color." }, "surfaceLight": { "type": [ "string", "null" ], "maxLength": 50, "description": "surfaceLight color." }, "shadow": { "type": [ "string", "null" ], "maxLength": 50, "description": "shadow color." } }, "additionalProperties": false } }, "required": [ "brand_kit_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "delete_brand_kit", "scope": "brand_kits:write", "description": "Delete an owned brand kit. Only when the user asks.", "inputSchema": { "type": "object", "properties": { "brand_kit_id": { "type": [ "string", "integer" ], "description": "Brand kit id returned by list_brand_kits or create_brand_kit." } }, "required": [ "brand_kit_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": true, "idempotentHint": true, "openWorldHint": false } }, { "name": "list_assets", "scope": "assets:read", "description": "List files uploaded to this account, newest first. Upload new files with REST multipart POST /v1/assets (field files, up to 5 files); MCP cannot carry file bytes.", "inputSchema": { "type": "object", "properties": { "limit": { "type": "integer", "minimum": 1, "maximum": 100, "description": "Items per page. Default 20." }, "offset": { "type": "integer", "minimum": 0, "description": "Items to skip. Default 0." } }, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "list_avatars", "scope": "avatars:read", "description": "List owned presenter avatars and quota. Only avatars with selectable=true can be used as video_config.avatar_id.", "inputSchema": { "type": "object", "properties": {}, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "list_voices", "scope": "voices:read", "description": "Find public catalog voices or your own clones. Choose voice_id from the returned items; never guess provider identifiers. Use samples on list/detail items for fixed audition clips.", "inputSchema": { "type": "object", "properties": { "voice_version": { "type": "integer", "description": "Voice I (1, default) or Voice II (2) for the public catalog. Private clone listings include both versions.", "enum": [ 1, 2 ] }, "type": { "type": "string", "description": "public shared catalog or private owned clones.", "enum": [ "public", "private" ] }, "language": { "type": "string", "description": "Optional language filter aligned with the platform catalog." }, "page": { "type": "integer", "description": "Page, starting at 1.", "minimum": 1 }, "limit": { "type": "integer", "description": "Items per page, up to 100.", "minimum": 1, "maximum": 100 } }, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "get_voice", "scope": "voices:read", "description": "Read a public or owned voice, including readiness and samples. Private voices from another account are unavailable. Poll this after clone_voice: a Voice II clone moves from training to trained (selectable=true) or failed.", "inputSchema": { "type": "object", "properties": { "voice_id": { "type": "string", "description": "Catalog or owned clone voice ID." }, "voice_version": { "type": "integer", "description": "Voice version of the voice: Voice I (1, default) or Voice II (2).", "enum": [ 1, 2 ] } }, "required": [ "voice_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "generate_audio", "scope": "audio:write", "description": "Synthesize up to 1,000 characters with a catalog voice or one of your ready clones, in Voice I or Voice II. voice_version must match the voice. Returns MP3 audio_url (which may be a data URL). Uses platform TTS pricing; reuse the same idempotency_key for retries.", "inputSchema": { "type": "object", "properties": { "text": { "type": "string", "description": "Spoken text.", "minLength": 1, "maxLength": 1000 }, "voice_id": { "type": "string", "description": "Catalog voice ID or owned ready clone ID." }, "voice_version": { "type": "integer", "description": "Voice version of voice_id: Voice I (1, default) or Voice II (2). Never substitute one version for the other.", "enum": [ 1, 2 ] }, "locale": { "type": "string", "description": "Speech locale. Voice II catalog voices accept their native or secondary locales; Voice II clones accept the locales they support." }, "speed": { "type": "number", "description": "Playback speed.", "minimum": 0.5, "maximum": 2 }, "idempotency_key": { "type": "string", "description": "Retry key for this operation. Generate a UUID once and reuse it only when retrying the same input. Never ask the user for it.", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$" } }, "required": [ "text", "voice_id", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "get_voice_clone_config", "scope": "voices:read", "description": "Read Voice II clone requirements before clone_voice with voice_version 2: availability, the authorized company_name, supported locales with the consent_statement the speaker must read aloud, and sample duration/size limits. When voice_ii_available is false (for example voice_ii_unavailable_reason clone_disabled), do not attempt a Voice II clone; offer Voice I instead.", "inputSchema": { "type": "object", "properties": {}, "required": [], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "clone_voice", "scope": "audio:write", "description": "Clone a private voice from audio already uploaded to your account. Voice I (default) is an instant clone from one sample. Voice II needs the speaker's consent: call get_voice_clone_config, have the speaker record the consent_statement for the chosen locale with their name and company_name filled in, upload it separately, then pass voice_talent_name, locale, consent_audio_url and consent_accepted=true. Never fabricate consent or set consent_accepted without the speaker's explicit agreement. Voice II returns 403 voice_ii_unavailable while cloning is not open for the account. Poll get_voice until state is trained or failed. Reuse idempotency_key on retry.", "inputSchema": { "type": "object", "properties": { "name": { "type": "string", "description": "Voice title.", "minLength": 1, "maxLength": 80 }, "audio_url": { "type": "string", "description": "Owned uploaded training audio URL. Voice II: 5–90 seconds of the same speaker." }, "cover_image_url": { "type": "string", "description": "Optional owned uploaded cover image URL. Voice I only." }, "voice_version": { "type": "integer", "description": "Voice I (1, default) or Voice II (2, consent-based personal voice).", "enum": [ 1, 2 ] }, "voice_talent_name": { "type": "string", "description": "Voice II only: the speaker's name exactly as spoken in the consent recording.", "minLength": 1, "maxLength": 128 }, "locale": { "type": "string", "description": "Voice II only: recording locale from get_voice_clone_config, for example en-US or zh-CN.", "maxLength": 16 }, "consent_audio_url": { "type": "string", "description": "Voice II only: owned uploaded recording of the speaker reading the consent_statement for locale. Must be a separate file from audio_url, at most 90 seconds." }, "consent_accepted": { "type": "boolean", "description": "Voice II only: true when the speaker has explicitly agreed that their voice may be cloned. Required for Voice II." }, "idempotency_key": { "type": "string", "description": "Retry key for this operation. Generate a UUID once and reuse it only when retrying the same input. Never ask the user for it.", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$" } }, "required": [ "name", "audio_url", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "delete_voice", "scope": "audio:write", "description": "Delete an owned cloned voice. Public catalog voices cannot be deleted. Reuse idempotency_key on retry.", "inputSchema": { "type": "object", "properties": { "voice_id": { "type": "string", "description": "Owned clone voice ID." }, "idempotency_key": { "type": "string", "description": "Retry key for this operation. Generate a UUID once and reuse it only when retrying the same input. Never ask the user for it.", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$" } }, "required": [ "voice_id", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": true, "idempotentHint": true, "openWorldHint": false } }, { "name": "get_avatar", "scope": "avatars:read", "description": "Read an owned avatar. status is the overall state (draft, generating, ready, failed, deleting, migration_required); training_status and preview_status track training and the preview sample; selectable must be true before video generation can use it; stage names the step in progress (queued, generating_training_video, provider_processing, generating_preview, deleting_provider_asset) or null when idle; error is {code, message} on failure. Training ready alone does not mean it can be used in a video.", "inputSchema": { "type": "object", "properties": { "avatar_id": { "type": "string", "description": "Owned avatar ID." } }, "required": [ "avatar_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "create_avatar", "scope": "avatars:write", "description": "Create an avatar from an owned asset_id or a public http(s) image/video URL. Third-party URLs are downloaded and archived to the caller’s owned storage before training. Requires platform entitlement. Poll get_avatar for preview_image_url and preview_video_url, or receive avatar.completed / avatar.failed through callback_url or a webhook subscription. Reuse idempotency_key on retry; never retrain automatically.", "inputSchema": { "type": "object", "properties": { "name": { "type": "string", "description": "Avatar name.", "minLength": 1, "maxLength": 80 }, "avatar_type": { "type": "string", "description": "Training source.", "enum": [ "human_video", "virtual_character" ] }, "asset_id": { "type": "string", "description": "Owned asset ID returned by POST /v1/assets. human_video uses a video asset; virtual_character uses an image asset." }, "image_url": { "type": "string", "description": "Public http(s) image URL. The backend archives third-party content to your owned storage before training. Use this or asset_id for virtual_character." }, "video_url": { "type": "string", "description": "Public http(s) training video URL. The backend archives third-party content to your owned storage before training. Use this or asset_id for human_video." }, "gender": { "type": "string", "description": "Required for image avatars.", "enum": [ "Male", "Female" ] }, "callback_url": { "type": "string", "description": "Optional public HTTPS URL notified once with avatar.completed or avatar.failed. Signed with the workspace callback secret (X-XPilot-Signature). Only set it when you run a receiving service.", "maxLength": 2048 }, "callback_id": { "type": "string", "description": "Optional reference echoed back as data.callback_id. Requires callback_url.", "maxLength": 128, "pattern": "^[\\w.:-]{1,128}$" }, "idempotency_key": { "type": "string", "description": "Retry key for this operation. Generate a UUID once and reuse it only when retrying the same input. Never ask the user for it.", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$" } }, "required": [ "name", "avatar_type", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "delete_avatar", "scope": "avatars:write", "description": "Delete an owned avatar. Poll get_avatar or list_avatars until it disappears. Reuse idempotency_key on retry.", "inputSchema": { "type": "object", "properties": { "avatar_id": { "type": "string", "description": "Owned avatar ID." }, "idempotency_key": { "type": "string", "description": "Retry key for this operation. Generate a UUID once and reuse it only when retrying the same input. Never ask the user for it.", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$" } }, "required": [ "avatar_id", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": true, "idempotentHint": true, "openWorldHint": false } }, { "name": "create_avatar_video", "scope": "avatars:write", "description": "Synthesize a talking-presenter video with an owned avatar whose training_status is ready. Drive it with text + voice_id (platform TTS, Voice I or Voice II) or with your own speech audio (asset_id or a public http(s) audio_url) — exactly one source, up to 5 minutes of speech. Output is a transparent-background WebM (VP9 with alpha) for compositing. Billed per rendered second at the digital-human video rate; the balance must cover the estimate before dispatch. Poll get_avatar_video, or receive avatar-video.completed / avatar-video.failed through callback_url or a webhook subscription. Reuse idempotency_key on retry; never resubmit automatically.", "inputSchema": { "type": "object", "properties": { "avatar_id": { "type": "string", "description": "Owned avatar ID with training_status ready." }, "text": { "type": "string", "description": "Spoken text for platform TTS. Use with voice_id; omit when sending audio.", "minLength": 1, "maxLength": 5000 }, "voice_id": { "type": "string", "description": "Catalog voice ID or owned ready clone ID from list_voices. Required with text." }, "voice_version": { "type": "integer", "description": "Voice version of voice_id: Voice I (1, default) or Voice II (2).", "enum": [ 1, 2 ] }, "locale": { "type": "string", "description": "Optional native locale for the voice." }, "speed": { "type": "number", "description": "TTS playback speed.", "minimum": 0.5, "maximum": 2 }, "audio_url": { "type": "string", "description": "Public http(s) speech audio URL (≤20 MB). The backend archives third-party audio to your owned storage first. Use this or asset_id instead of text." }, "asset_id": { "type": "string", "description": "Owned audio asset ID returned by POST /v1/assets. Use this or audio_url instead of text." }, "callback_url": { "type": "string", "description": "Optional public HTTPS URL notified once with avatar-video.completed or avatar-video.failed. Signed with the workspace callback secret (X-XPilot-Signature). Only set it when you run a receiving service.", "maxLength": 2048 }, "callback_id": { "type": "string", "description": "Optional reference echoed back as data.callback_id. Requires callback_url.", "maxLength": 128, "pattern": "^[\\w.:-]{1,128}$" }, "idempotency_key": { "type": "string", "description": "Retry key for this operation. Generate a UUID once and reuse it only when retrying the same input. Never ask the user for it.", "minLength": 8, "maxLength": 128, "pattern": "^[\\w.:-]{8,128}$" } }, "required": [ "avatar_id", "idempotency_key" ], "additionalProperties": false }, "annotations": { "readOnlyHint": false, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } }, { "name": "get_avatar_video", "scope": "avatars:read", "description": "Read an avatar video job: status (queued, processing, completed, failed), video_url (transparent WebM) once completed, duration_seconds, width, height and the settled cost_credits. Poll at least 5 seconds apart.", "inputSchema": { "type": "object", "properties": { "avatar_id": { "type": "string", "description": "Owned avatar ID." }, "video_id": { "type": "string", "description": "Video ID returned by create_avatar_video." } }, "required": [ "avatar_id", "video_id" ], "additionalProperties": false }, "annotations": { "readOnlyHint": true, "destructiveHint": false, "idempotentHint": true, "openWorldHint": false } } ] }