Audio & Voice
Everything for audio and voice, from transcription to editing. Turn speech into text in 90+ languages, generate subtitles, trim, merge, normalise and clean recordings, or read and write metadata. Each capability runs by API with the price published up front.
Align transcript to SRT timestamps
Each timestamp becomes one numbered SRT cue, and lines wrap at 42 characters by default without splitting words, so a corrected transcript keeps its original…
Free · Runs in your browser
Audiobook playback duration calculator
A 10-hour audiobook played at 1.5x takes 400 minutes, or six hours and forty minutes. Enter the listed length in minutes and your player speed to get the real…
Free · Runs in your browser
Audio file size calculator
A 180-second recording at 320 kbps comes to about 7.2 MB. Enter the running time in seconds and the target bitrate to check upload limits and storage before the…
Free · Runs in your browser
Convert audio channel layout
Going from 5.1 to stereo, the center and each surround reach their side at 0.707 and the LFE is left out.
Free · Runs in your browser
Crossfade duration calculator
Clips of 12.5 and 8.25 seconds joined by a 2.75-second crossfade play for 18 seconds in total, overlapping from 9.75 to 12.5 seconds.
Free · Runs in your browser
Convert decibels to linear amplitude
About 6.0206 dB doubles an amplitude, and 0 dB is a multiplier of exactly 1. Convert gains in either direction with the standard amplitude rule of 20 times the…
Free · Runs in your browser
DTMF Tone Frequency Lookup for Telephone Keypad Keys
Key 5 on a telephone keypad plays 770 Hz and 1336 Hz at the same time. Enter any digit from 0 to 9, the asterisk or the number sign to get its exact low and…
Free · Runs in your browser
Audio fade envelope calculator
A 12-second clip with a 2.5-second fade-in and a 3-second fade-out gets four points: silence at 0, full gain at 2.5 and at 9, and silence at 12 seconds.
Free · Runs in your browser
Generate a metronome click track specification from BPM and bars
At 120 BPM in 4/4, two bars give 8 clicks every 0.5 seconds, from 0 to 3.5, with the first beat of each bar accented and a total length of 4 seconds.
Free · Runs in your browser
Loudness normalization gain calculator
A master measured at -18.2 LUFS needs +4.2 dB to reach the -14 LUFS streaming target. Enter your meter reading and choose a target such as broadcast at -23 LUFS…
Free · Runs in your browser
Pitch shift frequency ratio calculator
Raising A4 at 440 Hz by 12 semitones gives a ratio of exactly 2 and a new frequency of 880 Hz. Enter any positive, negative or fractional shift to get the…
Free · Runs in your browser
Podcast chapter timestamp formatter
Chapters starting at 0, 83 and 3665 seconds become 00:00:00, 00:01:23 and 01:01:05, each followed by its title and ready to paste into show notes.
Free · Runs in your browser
Sample rate conversion ratio calculator
Going from 44,100 to 48,000 samples per second is an upsample with a ratio of 160:147. Enter any source and target rate to get the exact multiplier and…
Free · Runs in your browser
Silence detection threshold calculator for audio
A -60 dB noise floor with a 12 dB margin gives a -48 dB silence threshold and a 550 ms minimum gap.
Free · Runs in your browser
Audio tempo change calculator
Speeding a 240-second clip from 120 to 150 BPM is a 25% tempo increase, and the clip shrinks to 192 seconds.
Free · Runs in your browser
Trim audio by timestamp
A start at 30.5 seconds and an end at 95.25 seconds give a 64.75-second clip, checked against a 245.75-second recording.
Free · Runs in your browser
Adjust audio volume in decibels
A peak at -6 dBFS raised by 4.5 dB lands at -1.5 dBFS, leaving 1.5 dB of headroom and no clipping.
Free · Runs in your browser
Audio export preset lookup
Pick podcast and you get MP3 at a constant 128 kbps, 44.1 kHz, stereo: one coordinated starting point for the export dialog instead of a page of encoder…
Free · Runs in your browser
Peak normalization gain calculator
A recording that peaks at -8.4 dBFS needs +7.4 dB of gain to reach a -1 dBFS target. Enter the measured peak and the target, and get the gain to apply in your…
Free · Runs in your browser
Seamless loop crossfade calculator
A 120-second track with a 5-second crossfade starts fading at 115 seconds and repeats on a 115-second cycle.
Free · Runs in your browser
Calculate speaking rate in words per minute
450 words spoken in 180 seconds is 150 words per minute, right inside the typical 110 to 160 range.
Free · Runs in your browser
Concatenate audio clips
Clips of 12.5, 8.25 and 3 seconds add up to 23.75 seconds and start at 0, 12.5 and 20.75 seconds. Get every start time for chapters, captions or cue sheets…
Free · Runs in your browser
Format audio chapters for podcast apps
Three chapters starting at 0, 120 and 1800 seconds become one file that podcast apps read to show a table of contents and jump through the episode.
Free · Runs in your browser
Estimate audio duration after trimming silence
A 120-second clip with silences at 0 to 3.5, 42 to 47.25 and 110 to 120 seconds loses 18.75 seconds and runs 101.25 after trimming.
Free · Runs in your browser
Podcast ad slot timestamp calculator
In a 3600-second episode, ad slots at 2.5, 50 and 97.5 percent land at 90, 1800 and 3510 seconds, with readable timecodes such as 00:01:30.000.
Free · Runs in your browser
Ringtone clip window suggester
For a 215.4-second song whose chorus starts at 63.8 seconds, the suggested ringtone runs from 58.8 to 83.8 seconds.
Free · Runs in your browser
Compute multitrack mixdown gain from peaks and relative levels
A lead vocal peaking at -6 dBFS with the largest weight gets +6 dB, while a music bed at -3 dBFS with half that weight gets about -3.0206 dB.
Free · Runs in your browser
Shift karaoke lyrics timing by a global millisecond offset
Shift every lyric line with one value: with -1000 milliseconds, cues at 500, 1400 and 3200 ms move to 0, 400 and 2200 ms.
Free · Runs in your browser
Audio file size calculator
One CD-quality minute at 44100 Hz, 16-bit, stereo takes 10,584,000 bytes, or 10.584 MB, before any compression.
Free · Runs in your browser
Playback speed calculator
A 180-second clip played at 1.5x lasts 120 seconds, saving 60. Enter any duration and a positive speed, and the result comes back in the same unit you used…
Free · Runs in your browser
Port length calculator
Give it a 3-inch port, a 40 Hz tuning and a 2 cubic foot box, and it tells you how long to cut each tube, already net of the 2.196 inches the open ends add.
Free · Runs in your browser
Speaker box calculator
A driver with Vas 30 litres, Qts 0.4 and Fs 35 Hz wants a sealed box of about 14.12 litres, rolling off near 61.87 Hz.
Free · Runs in your browser
Transcribe audio
Send a recording in any of more than 90 languages and get back plain text you can search, quote or translate, instead of scrubbing to minute forty for one…
$0.004
Transcript with timestamps
Every word in the transcript comes with a start and end time in seconds, so a search result, a caption highlight or a video cut lands on the exact moment a…
$0.002
Subtitles as .srt
Send an audio track and get back a numbered .srt file whose lines break at natural pauses and appear in step with speech, ready for any video editor.
$0.002
WebVTT captions
Send an audio track and get back a .vtt file with the WEBVTT header, timed cues and readable lines, ready to link from the track element of an HTML5 video.
$0.002
Identify speakers
Turn a two-person interview or call into alternating turns labeled Speaker 1 and Speaker 2, each with its text and its start and end time.
$0.002
Detect the spoken language
Find out which language a recording is in without transcribing a single word, even on very short or noisy clips.
$0.002
Translate audio
Send a recording in one language and get back text in another in one job, with no separate transcription step whose mistakes would carry into the translation.
$0.004
Summarize audio
Skip the 60-minute replay: send the recording and get back a written summary that follows how the talk actually went, from a lecture's arc to an interview's…
$0.004
Meeting minutes
Turn a recorded meeting into minutes organized around decisions, owners and next steps that anyone can scan in under a minute.
$0.004
Action items
When someone says 'I'll circle back on that', it comes back as a commitment, tied to that speaker when the recording makes it clear.
$0.004
Podcast chapters
Send an episode and get back a list of chapters, each with a short title and its start time in seconds, placed where the conversation actually changes topic.
$0.004
Show notes
Upload the episode audio and get back a short summary, the key discussion points in order and a handful of quotes to highlight, ready for your podcast…
$0.004
Keywords from audio
Get a ranked list of the keywords and topics actually discussed in a recording, so you know what is inside before you listen.
$0.004
Audio to a blog post
Send a recording and get back an article draft with headings, paragraph breaks and a coherent flow, where false starts and filler words have been smoothed into…
$0.004
Moderate spoken audio
Check a voice message, call recording or podcast episode for harassment, threats or hate speech before it goes live, and see what was flagged and roughly where.
$0.004
Clean up a transcript
Turn the raw auto-transcript of a 45-minute episode into clean, punctuated paragraphs: fillers like 'um', repeated words and false starts go, while every…
$0.003
Search words in audio
Give it a recording and a list of words, and it returns every mention with its exact timestamp, so a reviewer listens to the seconds that matter instead of the…
$0.002
Text to speech
Send a text and get natural, well-paced narration back, with a download link that stays valid for 24 hours.
$0.005
SSML text to speech
Your SSML is accepted as is and read aloud naturally, but know the limit: a two-second break tag does not hold for two seconds, and emphasis tags do not stress…
$0.002
Spanish text to speech
Native Spanish voices read your text the way a Spanish narrator would: decimal commas, local currency and day-month-year dates sound natural instead of…
$0.002
Convert audio
Turn a phone voice memo in M4A into an MP3, or WAV session files into FLAC, so the next player, upload form or archive accepts the file.
$0.077
Trim audio
Pull the thirty seconds that matter out of a forty-minute recording: give a start point and how many seconds to keep, and only that clip comes back, cut cleanly…
$0.077
Normalize loudness
Bring every episode, chapter or voice clip to the same -16 LUFS loudness, so listeners stop reaching for the volume knob between files.
$0.077
Remove silence
A ninety-second dead spot is cut, while a half-second breath between sentences stays put. Upload a podcast, interview or voice memo and get back a tighter file…
$0.077
Reduce audio noise
Fan rumble, laptop hiss and the hum of old wiring are pulled down while the voice on top stays intact, because steady noise is told apart from speech.
$0.077
Merge audio
Join an intro jingle, a recorded interview and an outro sponsor read into one publish-ready episode file, in the order you list them.
$0.077
Split audio
Turn a ninety-minute recording into the pieces you need: chapters at exact timestamps, a two-minute teaser, or equal segments of a fixed length, each delivered…
$0.077
Audio metadata
Read the ID3 tags already inside an MP3, or write a new title, artist, album, track number or cover art, so podcast apps and music players stop showing 'Track…
$0.077