speech-to-text

belt app sample infsh/fast-whisper-large-v3 --save input.json
 
# {
#   "audio": "https://podcast.mp3",
#   "return_timestamps": "sentence"
# }
 
belt app run infsh/fast-whisper-large-v3 --input input.json

belt app run infsh/whisper-v3-large --input '{
  "audio": "https://french-audio.mp3",
  "task": "translate"
}'

# Extract audio from video first
belt app run infsh/video-audio-extractor --input '{"video_file": "https://video.mp4"}' > audio.json
 
# Transcribe the extracted audio
belt app run infsh/fast-whisper-large-v3 --input '{"audio": "<audio-url>"}'

# 1. Transcribe video audio
belt app run infsh/fast-whisper-large-v3 --input '{
  "audio": "https://video.mp4",
  "return_timestamps": "sentence"
}' > transcript.json
 
# 2. Pass the transcript segments as captions
belt app run infsh/caption-videos --input '{
  "video_file": "https://video.mp4",
  "segments": [{"start": 0.0, "end": 2.5, "text": "<segments-from-step-1>"}]
}'

# ElevenLabs STT (98%+ accuracy, diarization)
npx skills add inference-sh/skills@elevenlabs-stt
 
# ElevenLabs TTS (reverse direction)
npx skills add inference-sh/skills@elevenlabs-tts
 
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
 
# Text-to-speech (reverse direction)
npx skills add inference-sh/skills@text-to-speech
 
# Video generation (add captions)
npx skills add inference-sh/skills@ai-video-generation
 
# AI avatars (lipsync with transcripts)
npx skills add inference-sh/skills@ai-avatar-video