π·πΊ Π ΡΡΡΠΊΠΈΠΉ
πΊπΈ English
π¨π³ δΈζ
π€ OpenAI TTS
π OpenAI API Key
π€ TTS Model
Loading models...
π Text to Speech
π Speech Instructions (GPT models only)
You can control: accent, emotions, intonation, speed, tone
π£οΈ Voice
Alloy
Ash (new)
Ballad (new)
Coral (new)
Echo
Fable
Nova
Onyx
Sage (new)
Shimmer
π§ Audio Format
MP3 (default)
Opus (low latency)
AAC (YouTube, mobile)
FLAC (lossless)
WAV (low latency)
PCM (raw data)
β‘ Speech Speed (legacy models only)
0.25x
4.0x
1.0x
For GPT models use instructions above
π€ Generate Speech
Preparing request...
Initialization...
0%
β Audio ready!
β¬οΈ Download audio