Full Pipeline
Speech-to-Text → Translation → Text-to-Speech
Pipeline Stages
Speech to Text
Language
0 1
Corrects STT output or uploaded transcripts via Gemini.
Gemini Model
1 30
5 120
Translation
Text to Speech
Voice
0.5 1
0.5 1
Edits are saved to disk and used on the next pipeline run.
Use {target_language} as a placeholder for the target language.
Segments
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Segment
Custom phonetic spellings applied before synthesis.