LOVO?

NOT REALLYA prototype of the interface is possible, but the durable product depends on difficult systems beyond the UI. Build a safer adjacent workflow instead.

BUILD FIRST

A non-sensitive or read-only version of the core experience
A manual review step wherever correctness or trust matters
A narrow companion tool that removes a real piece of work

LEAVE FOR LATER

Regulated decisions, payments, or irreversible actions
Claims of correctness, compliance, or uptime that the MVP cannot support
Sensitive integrations until security, support, and auditability are ready

RESEARCH NOTES

What this tool actually does.

Checked 2026-09-06

LOVO (lovo.ai) is a voice AI platform centered on Genny, a browser-based text-to-speech and voiceover production tool. Genny turns typed or pasted scripts into editable blocks, offers 500+ voices across 100+ languages and accents, and includes Pro V2 voices that accept natural-language directions in square brackets (e.g., emotions, speed, accent). Users can adjust emphasis, speed, pauses, and pronunciation (via a Pronunciation Editor), add non-verbal sounds and sound effects, place audio on an editing timeline alongside video, and export as WAV, MP3, or MP4. Projects are stored in the cloud and accessed from the browser. The core workflow is: choose a voice, write/upload text, generate audio, edit parameters, then export.

SOURCES

RESEARCHED BUILD PROMPT

Give this to your coding agent.

Build a focused replacement for LOVO's Genny voiceover workflow: a browser-based AI voice-over studio where a user pastes a script, the app splits it into editable sentence blocks, the user picks a voice from a filterable library, clicks generate to produce TTS previews, then fine-tunes each block using speed, emphasis, pause, and pronunciation overrides. Users can add natural-language directions in square-bracket syntax (e.g., [sad], [fast]) before a block. Assemble the generated audio on a simple timeline with an optional background video track, then export as MP3, WAV, or MP4. Requirements: user authentication, cloud project save/load, voice library searchable by language/age/gender/tags, waveform preview using Web Audio API, per-block parameter controls, and export via FFmpeg. Implementation: React/Next.js frontend, Node/Python backend, abstract a TTS provider interface (e.g., ElevenLabs or Azure TTS) so providers can be swapped, serverless functions for export jobs, S3 for audio assets, JSON for project data. Do not copy LOVO's brand, UI, voice names, or exact visual design — create an original interface. Out of scope: voice cloning, real-time streaming, mobile apps, multi-track music editing, and marketplace features. Include a README with setup steps, environment variable list, API contract, and limitations (TTS latency, provider quotas, no offline use, and voice licensing/resale restrictions).

Visit the official product page