# llms.txt for https://omnivoice.app
# This file provides guidance to LLM crawlers on what content and concepts
# are important on the OmniVoice website, to improve semantic SEO coverage.

# -------------------------------------
# ✅ Website Information
Website: https://omnivoice.app
Name: OmniVoice
Description: OmniVoice is a free, open-source AI voice and audio platform with multilingual text-to-speech in 646 languages, zero-shot voice cloning, text-only voice design, AI voice changing, speech-to-text, video-to-text, and dedicated workflows for TikTok voiceovers, Seed Audio 1.0 cinematic one-prompt audio, Stable Audio 3.0-style music and SFX, Gemini 3.1 Flash TTS, and VoxCPM2. It targets creators, studios, and developers who need production-grade voice and audio generation with commercial use supported.

# Primary topics / entities:
# - "OmniVoice" AI voice generator and audio studio
# - multilingual Text to Speech (TTS) in 646 languages (/omni-voice-tts)
# - zero-shot Voice Cloning from 3–25 seconds of audio (/voice-cloning)
# - cross-lingual Voice Cloning (clone once, speak any language)
# - text-only Voice Design (/voice-design)
# - AI Voice Changer for speech-to-speech workflows (/ai-voice-changer)
# - Speech To Text and Video To Text (/speech-to-text, /video-to-text)
# - TikTok Voice Generator for short-form voiceovers (/tiktok-voice-generator)
# - Seed Audio 1.0 — cinematic AI audio from one prompt (/seed-audio-1-0)
# - Stable Audio 3.0 AI Audio Generator — music, SFX, loops (/stable-audio-3)
# - Gemini 3.1 Flash TTS and VoxCPM2 model pages
# - language landing pages: Spanish, French, Japanese, Hebrew, Arabic TTS
# - open-source Apache 2.0 license, commercial use allowed
# - comparisons vs ElevenLabs and PlayHT (WER, speaker similarity, speed)

# -------------------------------------
# ✅ Core Content Sections (based on actual page structure)
# These URLs are safe and recommended for deep crawling.
Allow: /
Allow: /omni-voice-tts
Allow: /voice-cloning
Allow: /voice-design
Allow: /ai-voice-changer
Allow: /speech-to-text
Allow: /video-to-text
Allow: /tiktok-voice-generator
Allow: /seed-audio-1-0
Allow: /seed-audio-1-0#tool
Allow: /seed-audio-1-0#showcase
Allow: /seed-audio-1-0#faq
Allow: /stable-audio-3
Allow: /stable-audio-3#audio-console
Allow: /stable-audio-3#pricing
Allow: /gemini-3-1-flash-tts
Allow: /voxcpm2
Allow: /spanish-text-to-speech
Allow: /french-text-to-speech
Allow: /japanese-text-to-speech
Allow: /hebrew-text-to-speech
Allow: /arabic-text-to-speech
Allow: /pricing
Allow: /how-to-use
Allow: /blog
Allow: /omnivoice-review
Allow: /omnivoice-vs-playht
Allow: /#hero
Allow: /#key-features
Allow: /#use-cases
Allow: /#comparisons
Allow: /#faqs

# -------------------------------------
# ✅ Important Legal / Policy Pages
Allow: /terms
Allow: /privacy
Allow: /refund

# -------------------------------------
# ❌ Disallowed API or Internal Paths
# These paths are not user-facing marketing content and should be ignored
# for content and reasoning.
Disallow: /api/
Disallow: /admin/
Disallow: /sign-in
Disallow: /sign-up
Disallow: /profile
Disallow: /sso-callback
Disallow: /share/

# -------------------------------------
# 📌 Sitemap for better discovery
Sitemap: https://omnivoice.app/sitemap.xml

# -------------------------------------
# 🎯 Key Product Capabilities to Understand

# 1) Multilingual Text to Speech (/omni-voice-tts)
# - 646-language coverage from a single unified model
# - natural prosody and intonation across language families
# - pronunciation control via phoneme annotations and Pinyin
# - configurable speaking rate (approx. 0.5×–2.0× real-time speed)

# 2) Zero-Shot Voice Cloning (/voice-cloning)
# - clone any voice from 3–25 seconds of reference audio
# - automatically extracts speaker timbre, accent, and rhythm
# - no training or fine-tuning pipeline required
# - cross-lingual: one cloned voice can speak any supported language
# - robust to noisy or imperfect reference recordings

# 3) Voice Design from Text (/voice-design)
# - create a synthetic voice using only a text description
# - supports attributes like gender, age, pitch, accent, style, emotion
# - enables rapid experimentation with many voices without recording

# 4) AI Voice Changer (/ai-voice-changer)
# - speech-to-speech voice transformation with reference audio
# - suited for video dubbing, localization, and character voice swaps
# - upload source audio plus a reference voice clip to reshape delivery

# 5) Speech To Text and Video To Text
# - /speech-to-text: transcribe speech into polished, editable text
# - /video-to-text: convert spoken content in videos into transcripts

# 6) TikTok Voice Generator (/tiktok-voice-generator)
# - short-form voiceover workflow for hooks, storytimes, promos, and memes
# - pairs curated public voices with TTS generation and export
# - not affiliated with TikTok; creator-focused workflow page on OmniVoice

# 7) Seed Audio 1.0 (/seed-audio-1-0)
# - cinematic AI audio generation from a single prompt
# - one-pass output: multi-character dialogue, SFX, background music, ambience
# - demo templates for radio drama, podcast, and brand-ad style scenes
# - long-form voice consistency and zero-shot cloning positioning
# - compared against traditional TTS and multi-track DAW workflows on-page
# - hero H1: "Seed Audio 1.0 — Cinematic AI Audio from One Prompt"

# 8) Stable Audio 3.0 AI Audio Generator (/stable-audio-3)
# OmniVoice offers Stable Audio 3.0-inspired music and sound-effect workflows; OmniVoice is not the official Stable Audio product.
# - Text to Music: background music, loops, intros, emotional beds from text prompts
# - AI Sound Effect Generator: UI feedback, game actions, transitions, cinematic hits
# - Flexible duration control and audio continuation / inpainting workflows
# - Studio console (#audio-console): prompt shaping, preview, MP3/WAV export
# - Credit-based pricing shared with voice, cloning, and voice design

# 9) Model and Language Landing Pages
# - /gemini-3-1-flash-tts: Google Gemini voice generation workflow
# - /voxcpm2: tokenizer-free TTS and cloning
# - /spanish-text-to-speech, /french-text-to-speech, /japanese-text-to-speech,
#   /hebrew-text-to-speech, /arabic-text-to-speech: localized TTS landing pages

# 10) Developer and Product Use Cases
# - audiobooks, podcasts, and long-form content narration
# - game NPC dialogue and character voices
# - language learning and pronunciation tutors
# - customer support and virtual assistants
# - news, announcement, and broadcast-style voices
# - ads, social clips, dubbing, and multilingual reposts

# 11) Performance and Benchmarks
# - multilingual WER ~2.85% vs ElevenLabs ~10.95% (24-language benchmark)
# - higher speaker similarity (SIM-o 0.830 vs 0.655)
# - ~45× faster than real-time on batch inference (RTF ≈ 0.022)
# - trained on ~581K hours of open-source speech data

# 12) Licensing and Openness
# - released under Apache 2.0 license
# - free tier available; paid credits for scale and commercial workflows
# - open-source implementation and research paper available on GitHub / arXiv

```
Canonical-Name: OmniVoice
Also-Known-As: OmniVoice, omnivoice.app
Product-Pages: /omni-voice-tts, /voice-cloning, /voice-design, /ai-voice-changer, /tiktok-voice-generator, /seed-audio-1-0, /stable-audio-3, /gemini-3-1-flash-tts, /voxcpm2
```