1 / 13
AI Code & ProjectsNewMade with Claude Code

Resona — AI Voice Studio SaaS (Next.js 16 Source Code)

Text-to-speech SaaS with 14 voices, read-along, credits and Stripe. Full source.

AAANKY.AI0.00 reviews0 sales
₹2,499

Commercial license · GST calculated at checkout

Choose a license
  • Secure instant download
  • Free lifetime updates
  • 7-day refund policy
  • Licensed copy · live-site activation, development free

What's included

  • Full Next.js 16 source, TypeScript strict
  • Text-to-speech studio with a live stage
  • 14 voices in 7 languages, each with a preview
  • Read-along highlighting and a waveform player
  • Workspaces, history, favorites, ⌘K search
  • 12 ready-made scripts in 8 categories
  • Credits per 100 characters, refunded on failure
  • Demo provider and an Anky AI provider stub
  • Plans and prices set in the admin, synced to Stripe
  • Better Auth: passkeys, Google, magic link, codes
  • Admin: users, plans, blog CMS
  • Licence activation with your purchase code
  • Prisma schema, migrations, demo seed
  • 35 unit tests (Vitest)
  • AGENTS.md, CLAUDE.md, Cursor and Windsurf rules
  • README, FEATURES, CHANGELOG, architecture docs
  • 13 screenshots from the production build
Framework
Next.js 16
Language
TypeScript
Database
PostgreSQL + Prisma
AI
Resona v1, Resona v1 Flash
Auth
Better Auth
Deploy
Vercel, Any Node host, Docker
File size
25.4 MB
Version
v1.0.1
Updated
Sep 28, 2026

Technical details

Made with

Claude Code

Model: Claude Opus 5.5

Built and documented with Claude Code on Claude Opus 5.5.

Works with

  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • GitHub Copilot
  • Windsurf

AGENTS.md and docs/ai/ let agents change it without scanning the repo.

Try it

Demo accounts
User and admin, one click
Demo generation
Pre-rendered sample reads, no API cost
Sample workspaces
Five per demo account
Real speech
Implement the Anky AI voice provider

Licences

Code
Your ANKY.AI tier (LICENSE.md)
Activation
Purchase code on your live site
Dependencies
Their own open-source licences
Demo voices
Local demo only; replace before launch

Resona is a complete AI text-to-speech studio: type or paste a script, pick one of 14 voices in 7 languages, tune speed, stability, similarity and style, and get speech in a waveform player with read-along highlighting. A live stage shows the voice's artwork and your script in large type, the bottom player keeps playing across pages with a queue and media keys, and every take lands in workspaces and a searchable history with favorites and downloads.

Around it sits a production platform: credits per started 100 characters, reserved atomically and refunded once on failure or cancel; Pro voices on paid plans, enforced on the server; plans and prices you set in the admin, synced to Stripe, with a customer portal and a trial; Better Auth with passkeys, Google, magic links and email codes; per-user rate limits and owner-checked downloads; and an admin with users, plans and a blog. Dark by default with a matching light theme, from 375px phones to large desktops.

Out of the box it runs in demo mode: the built-in demo provider plays pre-rendered sample reads through the real task lifecycle, with sentence timings and waveforms, and no API calls or cost. Real speech needs a voice API: the Anky AI provider ships as a stub for you to implement (docs/voice-generation.md walks through it). The bundled demo reads are for trying the studio locally; replace them before a public launch, as the README explains. AGENTS.md, CLAUDE.md, Cursor and Windsurf rules and a codebase map let Claude Code, Codex or Cursor connect a provider and rebrand it with you.

What you are buying: The full Next.js 16 source of Resona: the voice studio, the generation engine with its demo provider and an Anky AI provider stub, credits and admin-managed plans, workspaces and history, the persistent player, the admin, the database schema and demo seed, and the docs. Deploy it on Vercel or any Node host with PostgreSQL.

Third-party costs: Demo generation plays pre-rendered sample reads and costs nothing. Real speech runs on a voice API you connect by implementing the provider stub, and that API bills your account for what you generate. Stripe, an email provider and S3 or R2 storage are optional and bill you directly.

Resona · AI voice studio

Launch your own AI voice app
from script to speech in one click

Text-to-speech with 14 voices, read-along highlighting, a waveform player that follows you across pages, workspaces, credits and admin-managed plans, ready to rebrand and connect to your voice API.

  • Full source
  • 14 voices
  • Read-along
  • Dark, light & mobile
Resona voice studio with the stage, script and settings

14

Voices

7

Languages

12

Ready-made scripts

2,000

Characters per take

35

Unit tests

Everything included

Everything a voice SaaS needs

  • A studio, not a form

    A live stage with the voice's artwork and your script in large type, a script editor with ⌘↵, and settings beside it.

  • 14 voices, 7 languages

    American, British, Australian, Irish, Indian and South African English, plus Spanish, French, German, Portuguese, Japanese and Hindi.

  • Tune the delivery

    Two models, speed, stability, similarity and style, with automatic language detection you can override.

  • Read-along and a real player

    The sentence being spoken lights up; the bottom player keeps playing across pages with a waveform, a queue and media keys.

  • Workspaces and history

    A workspace per channel or client, a searchable history with favorites, audio detail pages and ⌘K search.

  • Credits, plans and admin

    Credits per 100 characters with automatic refunds, Pro voices on paid plans, and plans you price in the admin, synced to Stripe.

How it works

From script to speech

  1. 1

    Write or pick a script

    Type up to 2,000 characters or start from one of 12 ready-made scripts; the language is detected as you type.

    Script templates in eight categories
  2. 2

    Choose a voice

    Browse 14 voices with previews and filters, then tune speed, stability, similarity and style.

    Explore voices with previews and filters
  3. 3

    Generate and listen

    Honest staged progress, then the take plays in the bottom player with read-along highlighting.

    Speech rendering on the studio stage
  4. 4

    Keep and reuse

    Favorite, download or share takes, restore a take's text and settings, and find everything in History.

    History with search, favorites and voice filter

Who it's for

Ship a voice product fast

  • Founders

    Launch a paid text-to-speech product with sign-in, credits, plans and admin already built.

  • Agencies and studios

    White-label a branded voice tool for clients from one config file and one CSS file.

  • Video creators

    Voice-overs, intros and narration, organized in a workspace per channel.

  • Podcasters and publishers

    Openers, news briefs and audio versions of articles, with downloads and history.

  • Educators

    Lesson narration in several languages and accents.

  • Developers

    A clean reference for async AI tasks, a persistent audio player and read-along timing.

Make it yours

Customize it with Claude Code

The repo ships with AGENTS.md, CLAUDE.md and a codebase map. Open it in Claude Code, Codex or Cursor and ask in plain words:

  • “Implement the Anky AI voice provider with my API key and store the audio in my R2 bucket.”

  • “Rename it Voxcraft, switch the accent to emerald and use my logo.”

  • “Add two Pro voices with my own artwork and preview clips.”

  • “Charge 1 credit per 50 characters on the Flash model.”

Project specs

Everything you need to evaluate the stack at a glance.

Framework
Next.js 16
Language
TypeScript
Database
PostgreSQL + Prisma
AI models
Resona v1, Resona v1 Flash
Auth
Better Auth
Deployment
Vercel, Any Node host, Docker
Version
v1.0.1
Last updated
Sep 28, 2026

Tech stack

Ships with AGENTS.md, CLAUDE.md, GEMINI.md and .cursor/rules.

React 19Tailwind CSS 4shadcn/uiPrisma 7Better AuthStripeMotionWebGLreact-emailVitest
Package contentsAIinstruction files for coding agents
    • app/dashboard
    • app/api/voice
    • lib/audio-generation
    • lib/audio-generation/anky-provider.ts
    • components/voice
    • data
  • public/demo/voices
  • public/voices
  • .anky
  • README.md
  • FEATURES.md
  • CHANGELOG.md
  • LICENSE.md
  • AGENTS.mdAI
  • CLAUDE.mdAI
  • .env.exampleAI
  • docker-compose.yml
  • package.json
Quick start
$ npm install
$ cp .env.example .env
$ docker compose up -d
$ npm run db:migrate
$ npm run db:seed
$ npm run dev

Open the folder in Claude Code, Codex or Cursor and ask it to rebrand, add a feature or deploy — the instruction files explain the architecture and conventions.

#ai voice generator saas#text to speech app#tts saas source code#ai voice studio#nextjs saas source code#ai saas template#credits and stripe billing#audio player with waveform#better auth stripe prisma#claude code ready

More from ANKY.AI

View store