> ## Documentation Index > Fetch the complete documentation index at: https://bavlio.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Auto Derive Voice Config > Auto-derive an EDITABLE PERSONAL voice-config draft for the AUTHENTICATED user. Derives the personal voice for the caller — ``user_id`` is taken from the authenticated ``OrgContext`` (``org_context.user_id``), NEVER a client-supplied param, so a caller can only ever derive their OWN voice (anti-cross-user). The LinkedIn arm consumes the person's persisted ``person_identities`` enrichment (no scrape); the X arm reads the connected timeline; both feed an LLM voice analysis (the repo's standard Gemini path) whose contributions are merged into the personal voice (tone/style/topics/ do/don't + the read posts as editable sample snippets), with positioning pre-filled from the sender profile. The draft is NOT saved -- the UI lets the user review/edit and persist via PUT. ``linkedin_arm_status`` (ok / absent / error) and ``x_arm_status`` (derived / no_connection / needs_reauth / empty_timeline / unavailable) report each source independently. ## OpenAPI ````yaml https://api.bavlio.com/openapi.json post /api/v1/content/voice-config/auto-derive openapi: 3.1.0 info: title: Bavlio API description: >- Outreach automation API — lead enrichment, email campaigns, LinkedIn automation, and AI agent. Full docs at https://docs.bavlio.com. version: 1.0.0 x-guidance: product: Bavlio Data API protocols: - x402 description: >- Pay-per-call B2B data endpoints for AI agents. USDC on Base mainnet via x402 v2. See /openapi.json for pricing. Landing page + marketing details: https://bavlio.com/developers network: eip155:8453 docs_url: https://docs.bavlio.com x-payment-merchant-address: '0xcca4725e0e931982830bff523b141e1a7a58d3e7' servers: [] security: [] tags: - name: API Keys description: >- Create, list, and revoke API keys for programmatic access. JWT authentication required. - name: credits description: Credit balance, cost estimates, and transaction history. - name: campaigns description: Create, manage, launch, and monitor email campaigns. - name: campaign-personalization description: AI-powered email subject and body personalization for campaigns. - name: email-finder description: Find and verify email addresses for prospects. - name: sender-profiles description: Manage sender identity profiles for outreach. - name: sender-profile-chat description: Interactive chat for building sender profiles. - name: templates description: Email template CRUD. - name: suppression description: Do-not-contact suppression list management. - name: datasets description: Lead dataset listing, download, and updates. - name: user-extractions description: Uploaded lead file management and processing. - name: enrichment-chat description: Interactive chat for data enrichment sessions. - name: enrichment-processing description: Batch lead enrichment processing. - name: File Upload (CSV/Excel) description: Upload and preview CSV/Excel lead files. - name: connected-accounts description: LinkedIn account connections via Unipile. - name: linkedin-content description: LinkedIn post creation, scheduling, and management. - name: linkedin-playground description: Direct LinkedIn actions (profile lookup, messaging, engagement). - name: bavimail-proxy description: BaviMail domain, alias, and email management. - name: agent description: Bavi AI agent chat with SSE streaming. - name: notifications description: Notification preferences and delivery. - name: referral description: Referral code management and stats. - name: feedback description: User feedback submission. - name: authentication description: JWT token verification and user info. - name: users description: User quota and usage information. - name: Health description: Health checks and system status. - name: Personalization description: Core lead personalization engine. - name: Session Management description: Enrichment session lifecycle. - name: Session Processing description: Session data processing. - name: webhooks description: Inbound webhook handlers (Stripe, BaviMail, Unipile). paths: /api/v1/content/voice-config/auto-derive: post: tags: - content summary: Auto Derive Voice Config description: >- Auto-derive an EDITABLE PERSONAL voice-config draft for the AUTHENTICATED user. Derives the personal voice for the caller — ``user_id`` is taken from the authenticated ``OrgContext`` (``org_context.user_id``), NEVER a client-supplied param, so a caller can only ever derive their OWN voice (anti-cross-user). The LinkedIn arm consumes the person's persisted ``person_identities`` enrichment (no scrape); the X arm reads the connected timeline; both feed an LLM voice analysis (the repo's standard Gemini path) whose contributions are merged into the personal voice (tone/style/topics/ do/don't + the read posts as editable sample snippets), with positioning pre-filled from the sender profile. The draft is NOT saved -- the UI lets the user review/edit and persist via PUT. ``linkedin_arm_status`` (ok / absent / error) and ``x_arm_status`` (derived / no_connection / needs_reauth / empty_timeline / unavailable) report each source independently. operationId: auto_derive_voice_config_api_v1_content_voice_config_auto_derive_post responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AutoDeriveVoiceResponse' '401': description: Unauthorized security: - HTTPBearer: [] components: schemas: AutoDeriveVoiceResponse: properties: user_id: type: string title: User Id default: '' tone: type: string title: Tone default: '' style: type: string title: Style default: '' positioning: type: string title: Positioning default: '' topics: items: type: string type: array title: Topics do_guidelines: items: type: string type: array title: Do Guidelines dont_guidelines: items: type: string type: array title: Dont Guidelines sample_snippets: items: type: string type: array title: Sample Snippets linkedin_arm_status: type: string title: Linkedin Arm Status linkedin_arm_detail: type: string title: Linkedin Arm Detail default: '' x_arm_status: type: string title: X Arm Status x_arm_detail: type: string title: X Arm Detail default: '' type: object required: - linkedin_arm_status - x_arm_status title: AutoDeriveVoiceResponse description: >- An auto-derived, EDITABLE PERSONAL voice-config PRE-FILL (V2.1a re-key). NOT saved -- the UI hands the (user-edited) fields to the existing PUT to persist. The voice fields mirror ``VoiceConfigResponse`` so the UI can pre-fill the same form. ``user_id`` is whose personal voice this draft is for (the authenticated actor, echoed back; the client never supplies it). Per-arm status fields report how each source resolved: ``linkedin_arm_status`` (ok / absent / error — the arm now CONSUMES the person's persisted LinkedIn enrichment, no scrape) and ``x_arm_status`` (derived / no_connection / needs_reauth / empty_timeline / unavailable), each with an optional content-free ``*_detail``. securitySchemes: HTTPBearer: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.