audio
W
Whisper Transcription
Transcribe speech to text with timestamps and SRT output.
Try Whisper Transcription
Generating withWhisper Transcription3c per generation
Created with Whisper Transcription
Features
- Timestamps
- SRT output
- 100+ languages
- Speaker detection
Specifications
- Languages
- 100+
- Output
- Text + SRT
Input Requirements
Audio/Video*
audio upload
Language(optional)
select
Related Models
ElevenLabs TTS
100+ voices, natural TTS
2 credits · $0.02+
ElevenLabs Sound Effects
AI sound effects from text
3 credits · $0.03+
Stable Audio
AI music generation
5 credits · $0.05+
ElevenLabs Voice Clone
Clone any voice in 30s
5 credits · $0.05
ElevenLabs Translate
AI dubbing to 10+ languages
10 credits · $0.10
ElevenLabs Audio Isolation
Vocal isolation & denoising
3 credits · $0.03
ElevenLabs Voice Convert
Voice-to-voice transform
3 credits · $0.03
MiniMax Voice Design
Custom voices from text prompt
5 credits · $0.05
Frequently Asked Questions
How much does Whisper Transcription cost?
Whisper Transcription costs 3 credits per generation (~$0.03). New accounts get 50 free credits to try it.
How long does Whisper Transcription take to generate?
Typical generation time is ~10s. Speed depends on resolution and settings.
Can I use Whisper Transcription outputs commercially?
Yes, all content generated with Whisper Transcription on Arteza comes with a commercial license.
What file format does Whisper Transcription output?
High-quality PNG images at your chosen resolution.