NaturalReader

Build the following focused alternative to NaturalReader. This is a deliberately limited personal or small-team substitute, not parity with the paid service.

WORKING SLICE
Import user-owned text, choose a licensed voice, listen by paragraph and export synthetic audio with source/voice metadata.

SETUP AND ARCHITECTURE
Use Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface. Prerequisites: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success.

DOMAIN MODEL AND INVARIANTS
Store Document, Paragraph, PronunciationOverride, SpeechJob and AudioSegment; edited paragraphs invalidate only their derived audio and playback order follows the document revision.

IMPLEMENTATION CONTRACT
Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content.

APP-SPECIFIC BOUNDARY AND RECOVERY
Start with one supported voice engine and disclose synthesis. Do not clone a real person's voice or imply reading/OCR is flawless; scanned pages need a reviewed text-extraction step.

ACCEPTANCE SCENARIO
Correct a proper-name pronunciation midway through a chapter; regenerate affected segments without duplicating or skipping surrounding paragraphs. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested.

DELIVERY
Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product.

PROJECT RULES FOR AGENTS.md
Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication.

# AGENTS.md — Build guide for NaturalReader

## Project scope
Import user-owned text, choose a licensed voice, listen by paragraph and export synthetic audio with source/voice metadata.

Catalogue verdict: kinda. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For NaturalReader, read user-provided text and documents aloud with a small set of licensed or local voices. The hard boundary is voice catalog, ocr, document formats, mobile apps, and commercial licensing options, plus models, compute, rights, and safety operations.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- Runtime and tools: Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface.
- Before starting: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized.

## Stack and architecture
- Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface
- Data design: Store Document, Paragraph, PronunciationOverride, SpeechJob and AudioSegment; edited paragraphs invalidate only their derived audio and playback order follows the document revision.
- Setup: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized

## Security and data integrity
- Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location.
- Start with one supported voice engine and disclose synthesis. Do not clone a real person's voice or imply reading/OCR is flawless; scanned pages need a reviewed text-extraction step.
- Keep secrets outside client bundles and exported projects; document what leaves the device and make retention/deletion controls visible.

## Agent implementation rules
- Project rule — domain: Store Document, Paragraph, PronunciationOverride, SpeechJob and AudioSegment; edited paragraphs invalidate only their derived audio and playback order follows the document revision.
- Project rule — scope and recovery: Start with one supported voice engine and disclose synthesis. Do not clone a real person's voice or imply reading/OCR is flawless; scanned pages need a reviewed text-extraction step.
- Project rule — acceptance: Correct a proper-name pronunciation midway through a chapter; regenerate affected segments without duplicating or skipping surrounding paragraphs.
- Project rule — delivery: document real setup commands and permissions; do not claim a build, accuracy level, performance result or security certification that has not been demonstrated.

## Optional agent skills and references
- Recommended skill: [modern-python](https://github.com/trailofbits/skills/blob/main/plugins/modern-python/skills/modern-python/SKILL.md) — structure the Python worker or explicitly optional read-only utility with pinned dependencies, typed boundaries and clear failure handling. Follow the maintainer's installation instructions and match its requirements to the chosen runtime.
- Recommended skill: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — keep the proposed React work/review views responsive and avoid unnecessary rendering or data-fetch waterfalls. Follow the maintainer's installation instructions and match its requirements to the chosen runtime.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this working slice using synthetic or explicitly authorized non-sensitive examples: Import user-owned text, choose a licensed voice, listen by paragraph and export synthetic audio with source/voice metadata.
- Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Correct a proper-name pronunciation midway through a chapter; regenerate affected segments without duplicating or skipping surrounding paragraphs.
- State the limits before asking someone to replace their existing tool: Start with one supported voice engine and disclose synthesis. Do not clone a real person's voice or imply reading/OCR is flawless; scanned pages need a reviewed text-extraction step.

## Engineering roadmap
1. Phase 1 — Pin the working slice and create its example input: Import user-owned text, choose a licensed voice, listen by paragraph and export synthetic audio with source/voice metadata. Confirm setup: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized.
2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store Document, Paragraph, PronunciationOverride, SpeechJob and AudioSegment; edited paragraphs invalidate only their derived audio and playback order follows the document revision.
3. Phase 3 — Connect the working view to real saved state. Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location.
4. Phase 4 — Expose the app-specific limits and recovery path in context: Start with one supported voice engine and disclose synthesis. Do not clone a real person's voice or imply reading/OCR is flawless; scanned pages need a reviewed text-extraction step.
5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Correct a proper-name pronunciation midway through a chapter; regenerate affected segments without duplicating or skipping surrounding paragraphs. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

## Paid-product capabilities outside this build
- voice catalog, OCR, document formats, mobile apps, and commercial licensing options
- frontier voice or avatar model
- licensed voice catalog
- real-time rendering fleet
- moderation, consent verification, and enterprise rights

## Implementation prompt
Build the following focused alternative to NaturalReader. This is a deliberately limited personal or small-team substitute, not parity with the paid service.

WORKING SLICE
Import user-owned text, choose a licensed voice, listen by paragraph and export synthetic audio with source/voice metadata.

SETUP AND ARCHITECTURE
Use Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface. Prerequisites: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success.

DOMAIN MODEL AND INVARIANTS
Store Document, Paragraph, PronunciationOverride, SpeechJob and AudioSegment; edited paragraphs invalidate only their derived audio and playback order follows the document revision.

IMPLEMENTATION CONTRACT
Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content.

APP-SPECIFIC BOUNDARY AND RECOVERY
Start with one supported voice engine and disclose synthesis. Do not clone a real person's voice or imply reading/OCR is flawless; scanned pages need a reviewed text-extraction step.

ACCEPTANCE SCENARIO
Correct a proper-name pronunciation midway through a chapter; regenerate affected segments without duplicating or skipping surrounding paragraphs. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested.

DELIVERY
Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product.

PROJECT RULES FOR AGENTS.md
Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.