Create SFX
Speech to Speech
Text to Speech
×
Generate Story
Generate with OpenAI
Generate with Claude Sonnet
Click here to Generate Story JSON
Import JSON
Generating your story...
×
×
Generate Cover
?
×
5s
×
Speech to Speech
Voice:
Choose a voice for the conversion
Please select
Voice Model:
Select a voice model for this conversion. Each model has different capabilities and language support.
Please select
Upload Audio File:
Maximum file size: 50MB, Maximum duration: 300 seconds
Stability:
Adjust the stability of the voice (More variable / More stable). Lower values add variability for emotive performances, higher values ensure a more stable tone. Values under 0.3 may lead to instability.
VARIABLE
0.5
STABLE
Similarity:
Adjust how closely the AI mimics the original voice (Low / High). Higher values capture more nuances but may reproduce artifacts in poor quality audio.
LOW
0.75
HIGH
Style:
Adjust the style exaggeration of the voice (None / Exaggerated). Higher values amplify the original speakers style, adding more character. Values over 0.5 may lead to instability.
NONE
0.20
EXAGGERATED
Speaker Boost
Enable or disable speaker boost, which increases the similarity of the synthesized speech to the original voice. May slightly increase processing time.
Generate Speech to Speech
×
Text:
Enter the text you want to convert to speech (max. 5000 characters)
0/5000
Voice:
Choose a voice for the conversion
Please select
Voice Model:
Select a voice model for this conversion. Each model has different capabilities and language support.
Please select
Stability:
Adjust the stability of the voice (More variable / More stable). Lower values add variability for emotive performances, higher values ensure a more stable tone. Values under 0.3 may lead to instability.
VARIABLE
0.5
STABLE
Similarity:
Adjust how closely the AI mimics the original voice (Low / High). Higher values capture more nuances but may reproduce artifacts in poor quality audio.
LOW
0.75
HIGH
Style:
Adjust the style exaggeration of the voice (None / Exaggerated). Higher values amplify the original speakers style, adding more character. Values over 0.5 may lead to instability.
NONE
0.20
EXAGGERATED
Speaker Boost
Enable or disable speaker boost, which increases the similarity of the synthesized speech to the original voice. May slightly increase processing time.
Generate Text to Speech
×
×
×