Vibecode HeyGen

You are building a lean indie version of HeyGen.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# HeyGen indie build

## Goal

Build the smallest trustworthy replacement for the core HeyGen workflow for one developer or a tiny team.

## Scope

Turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- proprietary avatars, lip sync, translation, rendering, templates, and rights operations
- frontier voice or avatar model
- licensed voice catalog
- real-time rendering fleet
- moderation, consent verification, and enterprise rights

If those capabilities are essential, use Piper instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build a closest honest personal substitute for HeyGen in an empty repository.
Use Python 3.12, FastAPI, SQLite, ffmpeg, and a user-owned local TTS model; do not offer alternative stacks.
The core loop is: turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Require a project-level rights and consent acknowledgement before generating audio.
Ship with no celebrity, public-figure, or scraped voice assets and accept only explicitly licensed models.
Generate speech from text with voice, speed, pause, pronunciation, and segment controls.
Create a timeline for audio, captions, uploaded visuals, and simple transitions.
Embed project metadata and a visible synthetic-media disclosure in exported assets.
Store prompts, model identifiers, consent notes, and output hashes in a local provenance log.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Do not claim to reproduce proprietary data, network liquidity, regulated access, or frontier infrastructure.
Deliberately leave out cloning a voice without clear consent.
Deliberately leave out impersonation or deceptive unlabeled media.
Deliberately leave out a frontier avatar model, public hosting, or enterprise rights clearance.
Finish by running the tests and listing the exact commands used.

## Required capabilities

- local TTS model
- ffmpeg
- GPU recommended
- voices the user has rights and consent to use

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a lean indie version of HeyGen.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# HeyGen indie build

## Goal

Build the smallest trustworthy replacement for the core HeyGen workflow for one developer or a tiny team.

## Scope

Turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- proprietary avatars, lip sync, translation, rendering, templates, and rights operations
- frontier voice or avatar model
- licensed voice catalog
- real-time rendering fleet
- moderation, consent verification, and enterprise rights

If those capabilities are essential, use Piper instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build a closest honest personal substitute for HeyGen in an empty repository.
Use Python 3.12, FastAPI, SQLite, ffmpeg, and a user-owned local TTS model; do not offer alternative stacks.
The core loop is: turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Require a project-level rights and consent acknowledgement before generating audio.
Ship with no celebrity, public-figure, or scraped voice assets and accept only explicitly licensed models.
Generate speech from text with voice, speed, pause, pronunciation, and segment controls.
Create a timeline for audio, captions, uploaded visuals, and simple transitions.
Embed project metadata and a visible synthetic-media disclosure in exported assets.
Store prompts, model identifiers, consent notes, and output hashes in a local provenance log.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Do not claim to reproduce proprietary data, network liquidity, regulated access, or frontier infrastructure.
Deliberately leave out cloning a voice without clear consent.
Deliberately leave out impersonation or deceptive unlabeled media.
Deliberately leave out a frontier avatar model, public hosting, or enterprise rights clearance.
Finish by running the tests and listing the exact commands used.

## Required capabilities

- local TTS model
- ffmpeg
- GPU recommended
- voices the user has rights and consent to use

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a production product version of HeyGen.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== PRODUCT.md =====
# HeyGen product brief

## Problem

A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For HeyGen, assemble a labeled avatar-style video from user-owned media without cloning real people. The hard boundary is proprietary avatars, lip sync, translation, rendering, templates, and rights operations, plus models, compute, rights, and safety operations.

## Product outcome

Turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- local TTS model
- ffmpeg
- GPU recommended
- voices the user has rights and consent to use

## Explicit non-goals for v1

- proprietary avatars, lip sync, translation, rendering, templates, and rights operations
- frontier voice or avatar model
- licensed voice catalog
- real-time rendering fleet
- moderation, consent verification, and enterprise rights

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

===== ARCHITECTURE.md =====
# Architecture

## Starting brief

Build a closest honest personal substitute for HeyGen in an empty repository.
Use Python 3.12, FastAPI, SQLite, ffmpeg, and a user-owned local TTS model; do not offer alternative stacks.
The core loop is: turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Require a project-level rights and consent acknowledgement before generating audio.
Ship with no celebrity, public-figure, or scraped voice assets and accept only explicitly licensed models.
Generate speech from text with voice, speed, pause, pronunciation, and segment controls.
Create a timeline for audio, captions, uploaded visuals, and simple transitions.
Embed project metadata and a visible synthetic-media disclosure in exported assets.
Store prompts, model identifiers, consent notes, and output hashes in a local provenance log.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Do not claim to reproduce proprietary data, network liquidity, regulated access, or frontier infrastructure.
Deliberately leave out cloning a voice without clear consent.
Deliberately leave out impersonation or deceptive unlabeled media.
Deliberately leave out a frontier avatar model, public hosting, or enterprise rights clearance.
Finish by running the tests and listing the exact commands used.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

===== AGENTS.md =====
# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

===== MILESTONES.md =====
# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

===== OPERATIONS.md =====
# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted HeyGen capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# HeyGen indie build

## Goal

Build the smallest trustworthy replacement for the core HeyGen workflow for one developer or a tiny team.

## Scope

Turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- proprietary avatars, lip sync, translation, rendering, templates, and rights operations
- frontier voice or avatar model
- licensed voice catalog
- real-time rendering fleet
- moderation, consent verification, and enterprise rights

If those capabilities are essential, use Piper instead of pretending the gap is solved.

# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

# Build plan

## Original build brief

Build a closest honest personal substitute for HeyGen in an empty repository.
Use Python 3.12, FastAPI, SQLite, ffmpeg, and a user-owned local TTS model; do not offer alternative stacks.
The core loop is: turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Require a project-level rights and consent acknowledgement before generating audio.
Ship with no celebrity, public-figure, or scraped voice assets and accept only explicitly licensed models.
Generate speech from text with voice, speed, pause, pronunciation, and segment controls.
Create a timeline for audio, captions, uploaded visuals, and simple transitions.
Embed project metadata and a visible synthetic-media disclosure in exported assets.
Store prompts, model identifiers, consent notes, and output hashes in a local provenance log.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Do not claim to reproduce proprietary data, network liquidity, regulated access, or frontier infrastructure.
Deliberately leave out cloning a voice without clear consent.
Deliberately leave out impersonation or deceptive unlabeled media.
Deliberately leave out a frontier avatar model, public hosting, or enterprise rights clearance.
Finish by running the tests and listing the exact commands used.

## Required capabilities

- local TTS model
- ffmpeg
- GPU recommended
- voices the user has rights and consent to use

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

# HeyGen product brief

## Problem

A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For HeyGen, assemble a labeled avatar-style video from user-owned media without cloning real people. The hard boundary is proprietary avatars, lip sync, translation, rendering, templates, and rights operations, plus models, compute, rights, and safety operations.

## Product outcome

Turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- local TTS model
- ffmpeg
- GPU recommended
- voices the user has rights and consent to use

## Explicit non-goals for v1

- proprietary avatars, lip sync, translation, rendering, templates, and rights operations
- frontier voice or avatar model
- licensed voice catalog
- real-time rendering fleet
- moderation, consent verification, and enterprise rights

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

# Architecture

## Starting brief

Build a closest honest personal substitute for HeyGen in an empty repository.
Use Python 3.12, FastAPI, SQLite, ffmpeg, and a user-owned local TTS model; do not offer alternative stacks.
The core loop is: turn user-authored text into a clearly labeled avatar-style video assembled from user-owned media with a local model, never cloning real people, and retain provenance for every output.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Require a project-level rights and consent acknowledgement before generating audio.
Ship with no celebrity, public-figure, or scraped voice assets and accept only explicitly licensed models.
Generate speech from text with voice, speed, pause, pronunciation, and segment controls.
Create a timeline for audio, captions, uploaded visuals, and simple transitions.
Embed project metadata and a visible synthetic-media disclosure in exported assets.
Store prompts, model identifiers, consent notes, and output hashes in a local provenance log.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Do not claim to reproduce proprietary data, network liquidity, regulated access, or frontier infrastructure.
Deliberately leave out cloning a voice without clear consent.
Deliberately leave out impersonation or deceptive unlabeled media.
Deliberately leave out a frontier avatar model, public hosting, or enterprise rights clearance.
Finish by running the tests and listing the exact commands used.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted HeyGen capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

$ choose a build depth, inspect the files, then open the complete pack in your agent · this prompt is generated from the build plan · improve it via PR