Settings
Settings
×
OpenAI API Key
Required for OpenAI TTS. Get yours at platform.openai.com
Default Voice
Onyx
Alloy
Nova
Shimmer
Echo
Fable
Audio Model
OpenAI TTS model (tts-1 or tts-1-hd)
Auto-play audio when ready
Playback Speed
0.75x
1x
1.25x
1.5x (Default)
1.75x
2x
Save Settings
Doc to Audio
Drop a file
or click to browse
TXT, MD, DOCX, PDF
Browse Files
Paste Text
0 words
Est. $0.00
i
Pricing:
$15/1M chars (TTS-1)
Time:
~35s per 4000-char chunk
Parallel:
5 requests (tier3)
Onyx - Deep, authoritative
Alloy - Neutral, balanced
Nova - Warm, friendly
Shimmer - Clear, expressive
Echo - Soft, gentle
Fable - Storytelling, dramatic
Generate Audio
Preview (editable)
0:00
Ready
0:00
1.5x
Download