Media
Estimate speech clarity from level, noise separation, reverberant tails, high-frequency presence, clipping, and speech-band energy.
audio-speech-intelligibility-scoreMedia
Detect likely speech-range activity and export speech/non-speech ranges as JSON, CSV, SRT markers, or an FFmpeg cut list.
audio-voice-activity-segmentationMedia
Validate an audiobook chapter or full file against ACX/Audible submission requirements: RMS, peak, noise floor, duration, format, and chapters.
audio-audiobook-acx-validatorMedia
Add the required lead-in, lead-out silence, and room tone between audiobook chapters for ACX-compliant submission.
audio-audiobook-room-tone-inserterMedia
Generate sentence or word-level timestamp cues from a narration audio and its script, for karaoke-style reading and language learning.
audio-read-along-cue-generatorMedia
Estimate how long a script will take to read aloud, with optional calibration from a recorded sample.
audio-script-timing-estimatorMedia
Match loudness between a host and a guest track (or any two voice takes) while preserving natural dynamics.
audio-interview-level-matcherMedia
Insert ad-insertion markers into a podcast episode: audible beep tones, ID3 chapter markers, and metadata tags for programmatic ad insertion.
audio-podcast-ad-marker-inserterMedia
Automatically duck a music bed under voice/dialogue using sidechain compression, with fade-in/out templates for intros and outros.
audio-podcast-intro-outro-duckerMedia
Assemble a short podcast trailer from intro music, up to 5 highlight clips, a music bed under the clips, and a loudness target.
audio-podcast-trailer-builderMedia
Compare multiple recorded takes by noise, clipping, tempo, duration and consistency, then rank them to pick the best.
audio-voiceover-take-selectorMedia
Extract the background ambience/room tone from a fragment and generate a seamless loop of any target length.
audio-ambience-loop-generator