evo-dubbing-tts-synthesis
SkillSearchSynthesizes target-language speech from text using Kokoro TTS, with speed/duration control to fit precise time windows. Handles SRT parsing, text extraction, and produces WAV segments.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the evo-dubbing-tts-synthesis skill
What this skill tells your AI
The instructions your AI receives, as published by openlair/openskill in tasks-evolved/multilingual-video-dubbing/environment/skills/evo-dubbing-tts-synthesis/SKILL.md and read by ahel’s review.
Synthesizes target-language TTS audio fitted to SRT time windows using Kokoro.
Key Functions
parse_srt_file(path)- Parse SRT file, return list of dicts with index, text, start_sec, end_sec, duration_secread_target_language(path)- Read target language code from filesynthesize_segment(text, lang_code, voice, speed)- Generate audio array using Kokorofit_audio_to_window(text, lang_code, voice, target_duration)- Synthesize and adjust speed to fit windowgenerate_tts_segments(segments_srt, source_srt, target_srt, lang_code, output_dir)- Full pipeline
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-dubbing-tts-synthesis/scripts')
from utils import parse_srt_file, read_target_language, generate_tts_segments
segments = parse_srt_file('/root/segments.srt')
lang = read_target_language('/root/target_language.txt')
results = generate_tts_segments(
'/root/segments.srt', '/root/source_text.srt',
'/root/reference_target_text.srt', lang, '/outputs/tts_segments'
)
Technical Details
- Kokoro native sample rate: 24000 Hz
- Japanese lang_code for Kokoro: 'j'
- Default Japanese voice: 'jf_alpha'
- Speed parameter range: 0.5 to 2.0 for quality
- SRT time conversion: sub.start.ordinal / 1000.0 for seconds
- Use encoding='utf-8-sig' for BOM handling
Signals
- GitHub stars
- 89
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
evo-dubbing-tts-synthesis- Source
- github.com/openlair/openskill