# AGENTS.md — Build guide for Speechify

## Project scope
Import text, PDF or EPUB, inspect extracted reading order and generate speech with a locally installed TTS engine. Highlight the current segment, adjust playback speed and resume from a saved bookmark.

Catalogue verdict: kinda. Speechify's core reading loop is a weekend build: import documents, extract text, read it aloud with a natural local voice, highlight the current sentence, and save progress. The gap is product depth, including the size and consistency of Speechify's hosted voice catalog, OCR and mobile capture, cross-device sync, cloud-drive integrations, voice typing, AI podcasts, and document chat.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first. A compatible local TTS engine/voice model, permitted source documents and optional OCR software for scanned PDFs.
- Implementation components: Node.js, TypeScript and Express with server-rendered HTML and small browser modules. SQLite through better-sqlite3 with migrations, prepared statements and a single background worker. Local document extraction and a documented installed neural TTS engine behind a bounded subprocess adapter; audio cache keyed by text/voice hash.
- Scope boundary: Premium voices, publisher access and exact word alignment depend on the selected engine.

## Stack and architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Local document extraction and a documented installed neural TTS engine behind a bounded subprocess adapter; audio cache keyed by text/voice hash.
- Domain model: documents, extracted reading order, text segments, voice/model settings, audio chunks and playback bookmarks

## Security and data integrity
- Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.
- Correctness boundary: Chunk audio is keyed to text and voice revisions; OCR or reading-order uncertainty is shown before narration and no voice is cloned without authorization.
- Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
- Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

## Agent implementation rules
- Project rule — data model: documents, extracted reading order, text segments, voice/model settings, audio chunks and playback bookmarks
- Project rule — preserve this invariant: Chunk audio is keyed to text and voice revisions; OCR or reading-order uncertainty is shown before narration and no voice is cloned without authorization.
- Project rule — acceptance evidence: Edit a paragraph and regenerate only affected audio chunks; resuming a book opens the correct segment even after a browser restart.

## Optional agent skills and references
- Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [pdf](https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md) — Process PDFs through extraction, generation, page operations, form filling and OCR workflows. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.

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 the actual Speechify-inspired workflow with owned or clearly labeled sample data: Import text, PDF or EPUB, inspect extracted reading order and generate speech with a locally installed TTS engine. Highlight the current segment, adjust playback speed and resume from a saved bookmark.
- Publish a reproducible walkthrough with this observable result: Edit a paragraph and regenerate only affected audio chunks; resuming a book opens the correct segment even after a browser restart.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: Premium voices, publisher access and exact word alignment depend on the selected engine. Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import text, PDF or EPUB, inspect extracted reading order and generate speech with a locally installed TTS engine. Highlight the current segment, adjust playback speed and resume from a saved bookmark. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Premium voices, publisher access and exact word alignment depend on the selected engine.
2. Phase 2 — Durable model. Model documents, extracted reading order, text segments, voice/model settings, audio chunks and playback bookmarks Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Chunk audio is keyed to text and voice revisions; OCR or reading-order uncertainty is shown before narration and no voice is cloned without authorization.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Edit a paragraph and regenerate only affected audio chunks; resuming a book opens the correct segment even after a browser restart. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

## Paid-product capabilities outside this build
- Speechify's 1000+ hosted voices and consistent quality across devices
- mobile scanning and polished OCR capture
- cross-device sync and offline native apps
- Google Drive, Dropbox, and OneDrive integrations
- voice typing, AI podcasts, and document chat

## Implementation prompt
WORKING SLICE
Import text, PDF or EPUB, inspect extracted reading order and generate speech with a locally installed TTS engine. Highlight the current segment, adjust playback speed and resume from a saved bookmark.

Build this scoped Speechify-inspired workflow with a documented data model and visible failure states.

Architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Local document extraction and a documented installed neural TTS engine behind a bounded subprocess adapter; audio cache keyed by text/voice hash.

Prerequisites and limits
A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first. A compatible local TTS engine/voice model, permitted source documents and optional OCR software for scanned PDFs.
Outside this release: Premium voices, publisher access and exact word alignment depend on the selected engine.

Data model and correctness
documents, extracted reading order, text segments, voice/model settings, audio chunks and playback bookmarks
Invariant: Chunk audio is keyed to text and voice revisions; OCR or reading-order uncertainty is shown before narration and no voice is cloned without authorization.
Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.

Security and privacy
Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.

Recovery and export
Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import text, PDF or EPUB, inspect extracted reading order and generate speech with a locally installed TTS engine. Highlight the current segment, adjust playback speed and resume from a saved bookmark. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Premium voices, publisher access and exact word alignment depend on the selected engine.
2. Phase 2 — Durable model. Model documents, extracted reading order, text segments, voice/model settings, audio chunks and playback bookmarks Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Chunk audio is keyed to text and voice revisions; OCR or reading-order uncertainty is shown before narration and no voice is cloned without authorization.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Edit a paragraph and regenerate only affected audio chunks; resuming a book opens the correct segment even after a browser restart. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Edit a paragraph and regenerate only affected audio chunks; resuming a book opens the correct segment even after a browser restart.
Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees.

Optional agent guidance
Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [pdf](https://github.com/anthropics/skills/blob/main/skills/pdf/SKILL.md) — Process PDFs through extraction, generation, page operations, form filling and OCR workflows. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: documents, extracted reading order, text segments, voice/model settings, audio chunks and playback bookmarks
Project rule — preserve this invariant: Chunk audio is keyed to text and voice revisions; OCR or reading-order uncertainty is shown before narration and no voice is cloned without authorization.
Project rule — acceptance evidence: Edit a paragraph and regenerate only affected audio chunks; resuming a book opens the correct segment even after a browser restart.

## 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.