🎤 VoxScribe - Universal STT Platform

Device: Loading...

Dependencies: Checking...

Feature Selection

Speech-to-Text Text-to-Speech

STT Mode Selection

Single Model Compare Models

Model Selection

Engine:

Model:

Text-to-Speech Configuration

1

Choose TTS Provider

💻

Coqui TTS

Local • Free • Ready to Use

FREE

🌐

OpenRouter

Cloud • Free & Paid Models

FREEMIUM

💡 Note: OpenRouter is used for AI text optimization (LLM preprocessing), not for voice synthesis. Voice synthesis is done locally by Coqui TTS (free, no API key required).

Text Input

Enter text to convert to speech:

0 characters

Output Format

🎵

WAV Lossless

🎶

MP3 192kbps

🎼

FLAC Lossless

🔊

OGG Open Source

Audio Upload

Drag & drop audio file here or click to browse

Supported: WAV, MP3, FLAC, M4A, OGG

Voxtral Support: Checking...

NeMo Support: Checking...

Granite Support: Checking...

Loading history...

RTFx (Real-Time Factor) measures how fast transcription processes compared to audio duration.

2.5x 2.5× faster than real-time
1 min audio → 24 sec processing

150x 150× faster than real-time
1 min audio → 0.4 sec processing

0.5x Slower than real-time
1 min audio → 2 min processing

Higher RTFx = faster processing. 1x = real-time speed.

Whisper

✅ Detailed timestamps
✅ Multiple model sizes
✅ Fast processing
✅ Lower resource requirements

Voxtral

✅ Advanced audio understanding
✅ Multilingual support
✅ Long-form context (30 min)
🔧 Requires transformers 4.56.0+

NVIDIA (Parakeet & Canary)

✅ NVIDIA optimized models
✅ Fast inference
✅ Parakeet: Timestamps support
✅ Canary: State-of-the-art English ASR
🔧 Requires NeMo toolkit

Granite Speech

✅ IBM's compact speech model
✅ Two-pass design (ASR + language)
✅ Supports ASR and AST
✅ Chat-based interface
🔧 Requires transformers 4.57.0+

VoxScribe

Feature Selection

STT Mode Selection

Model Selection

Text-to-Speech Configuration

Choose TTS Provider

Choose OpenRouter Audio Model

Choose Language

Choose Gender

Choose Voice

AI Enhancement (Optional)

Text Input

Output Format

Audio Preview

Audio Upload

Results

Feature Selection

STT Mode Selection

Model Selection

Text-to-Speech Configuration

Choose TTS Provider

Choose OpenRouter Audio Model

Choose Language

Choose Gender

Choose Voice

AI Enhancement (Optional)

Text Input

Output Format

Audio Preview

Audio Upload

Results

Download Model

Downloading Model

Delete Model

Transcription History

Transcription Details