Skip to content
LOCAL TRANSCRIPTION · TRANSLATION · TTS · SUBTITLES

Turn one recording into a finished listening lesson.

Drop in up to five minutes of audio or video, or paste a text: it transcribes on this machine, splits the speech into sentences, translates into Chinese, English or Russian, narrates it, then exports five-minute MP3 parts with line-by-line lyrics — translated line first, original after, in whichever order you set. Nothing is uploaded.

FILES UPLOADED
0
LANGUAGES
ZH · EN · RU
CREDITS
DON'T EXPIRE

Windows 10/11 & macOS 12+ · 1.7 GB of required models, installed once · Export with the network off

aiwima echo — preview & export
AiWima Echo at the preview-and-export step: a player with line-by-line synced lyrics above an export summary — one MP3, 55 seconds, 1 credit used, 60 left.
LOCAL ASR · MT · TTSLOCAL
The export summary states the file count, the runtime, the credits this costs and what is left — before anything is charged.
  • Runs on your machine
  • Chinese · English · Russian
  • Pay per export
  • Merge & split included

HOW IT WORKS

Three steps, one wizard.

All three happen in the same app — and the three tabs in step two share one dataset, so nothing is redone when you switch.

  1. STEP 01

    Add your material

    Drop in up to five minutes of audio or video, or paste text (no length limit). Speech is transcribed on this machine.

  2. STEP 02

    Edit the content

    Translate, check the sentences, pick a voice and speed — three tabs over the same data: choose the target language, fix lines one by one, set voice and pacing.

  3. STEP 03

    Preview and export

    Listen through with scrolling lyrics. Output becomes 1.mp3, 2.mp3… at five minutes, each with matching lyrics. One credit per MP3.

The sentence table: five Chinese lines each paired with its English translation, with time, type and a per-row menu.

STEP 02 IN DETAIL

One sentence per line — edit one, nothing else moves.

Source and translation sit side by side, and any line opens for editing; sentences split, merge or stay whole. The timeline is computed before export, so the subtitles and the audio always share it.

The export dialog lists the credits it costs and what is left; a failed or cancelled export is not charged.

THE APP

What it looks like.

All three steps live in one window — no web dashboard, no plugin. The clip below is the app running, on a sample lesson.

Seventeen seconds end to end: add material → check the sentences → voice and speed → preview and export. The sample is five sentences, 55 seconds, one MP3.
Step one, add your material: a Chinese text pasted into the text box, with a live character count.
Add material: drop in audio or video, or paste a text — no length limit on text.
Voice and speed tab: male or female voice for the Chinese source and the English translation, four speed presets.
Voice and speed: a male and a female voice per language, four plain-language speeds.
Merge page: three numbered parts sorted by filename, each matched to its lyrics file.
Merge: parts sort by filename, lyrics match automatically, no credits spent.
Split page: two cut points divide one recording into three segments with per-segment lyric counts.
Split: cut by timestamp or evenly, and the lyric timeline follows.

WHAT IT DOES

From recording to finished lesson, in one pass.

Transcription, translation, narration, timing, splitting, subtitles, merging and cutting back — the work of four or five tools, in one place.

  • Transcribe: speech recognition with automatic sentence breaks.
  • Translate: Chinese, English and Russian, sentence by sentence.
  • Narrate: a male and a female voice per language, with speed and pause controls.
  • Interleave: each line's translation plays before the original, or after it — your choice, per lesson.
  • Time: subtitles are aligned for you, no manual stamping.
  • Split: anything over five minutes becomes 1.mp3, 2.mp3…, no part over five minutes.
  • Subtitles: .lrc by default, .srt and .vtt when you need them.
  • Merge: parts sort themselves by filename and go back into one lesson — free, unlimited.
  • Cut back: split one long file by timestamp or evenly, lyrics follow the cut — free, unlimited.
  • Your material stays on this computer — no account, no upload.

CREDITS

You pay for finished MP3s.

One exported MP3, one credit. Transcription, translation, previewing and re-editing cost nothing.

ONE EXPORTED MP3
1 credit
SUBTITLES (.lrc / .srt / .vtt)
Free
TRANSCRIBE, TRANSLATE, PREVIEW, RE-EDIT
Free
MERGE / SPLIT MP3 TOOLS
Free, unlimited
FAILED OR CANCELLED EXPORT
Not charged
EXPIRY
None

USE CASES

Who it's for

People who make listening material — and can't upload the source.

Language teachers

Material you already have becomes a week of listening practice in an afternoon: script, translation, narration, timing and split parts in one pass.

SCHOOLS · TUTORING · UNIVERSITY

Intranets & labs

Runs on the computers in the classroom or the lab. Nothing to whitelist, no student accounts to create.

LABS · INTRANET · CONFIDENTIAL

Self-learners

Turn your own study audio into bilingual subtitles, then work through it at the speed you actually follow.

INDEPENDENT · SELF-STUDY

PRICING

Pay per export. Three packs.

FROM $0.100 PER EXPORT · CREDITS NEVER EXPIRE

BASIC
$315 exports

$0.200 / export

One lesson's worth, to run the whole flow on real material.

  • All three languages, both voices each
  • Bilingual .lrc, plus .srt and .vtt
  • Free merge & split tools, unlimited
  • Credits never expire
  • One-time payment
Buy 15 exports
STANDARDMOST POPULAR
$1060 exports

$0.167 / export

A term's worth, and the pack most teachers pick.

  • Everything in Basic
  • Save $2 versus four Basic packs
  • Same machine code, credits stack
Buy 60 exports
PROLOWEST UNIT PRICE
$1001000 exports

$0.100 / export

A department, or a year of publishing. Lowest unit price.

  • Everything in Standard
  • $0.100 per export — 50% below the Basic unit price
Buy 1000 exports
  • One-time payment. No subscription, nothing renews.
  • Prices exclude tax — it is calculated at checkout.
  • Credits never expire and are bound to one machine.
  • Activation code delivered by email, instantly.

Pricing →

INCLUDED, FREE

Merge and split come with it.

A lesson arrives as numbered parts: the merge page drags them into order and returns one continuous MP3 with one merged lyrics file. The split page cuts one long recording by timestamp or evenly, and the lyric timeline follows the cut. Neither spends a credit.

  • Merge sorts by filename naturally, so 1.mp3 … 10.mp3 lines up by itself
  • Split points snap to the start of a sentence, so no line is cut in half
  • Lyrics match by filename — .srt / .vtt converted when there's no .lrc
  • Available once activated — no separate purchase

PURCHASE & ACTIVATION

How buying and activating work

  1. 01Install and copy your Machine Code
  2. 02Pick a credit pack
  3. 03Pay — the code arrives by email
  4. 04Activate once, then it all runs locally

One machine, one code

Credits are bound to the Machine Code of one computer. Buying a second pack for the same machine is fine — the credits add up.

Validation is local

Activation is checked by a local signature. The app never contacts a server to confirm your credits, and keeps working if this site is down.

New computer or a wrong code?

Codes cannot move by themselves. Changed machines, reinstalled the system, or typed the Machine Code wrong? Ask for a replacement carrying the credits you had left.

REFUNDS & REPLACEMENTS

  • Ask for a refund within 7 days of the charge — no reason required. Local consumer law may give you longer.
  • Replacement codes for a new computer, a reinstall or a mistyped Machine Code are free — write to support@aiwima.com.
  • Full refund policy →

FAQ

Questions, answered.

Still not sure? Write tosupport@aiwima.com

Does it need the internet?

No. AI recognition, AI translation, narration, timing and export all run on this computer. The only two places the network is used: downloading a model you pick, and a version check you start yourself.

Are my recordings uploaded?

No, and there is nowhere for them to go. They stay in the folder you took them from.

Which languages?

Chinese, English and Russian, any pair, with one male and one female voice each.

How long can a file be?

Input audio and video are capped at five minutes: anything longer is refused outright, not auto-cut — trim it first, then use the merge page to put the lesson back together. Text has no limit, and is split into numbered parts at five minutes when you export, with the count shown beforehand.

What costs a credit?

Only exported MP3s. Subtitles, transcription, translation, previewing, re-editing, and the merge and split tools are free, and a failed or cancelled export is not charged.

Do credits expire?

No. They stay on the machine code you activated until you use them.

Is there a trial?

Yes. Use the free-trial link, tell us your name, email and occupation, and we email you how to start. The early steps are free anyway: importing, transcription, translation, previewing and re-editing cost no credits — only a finished MP3 does.

Request a free trial

How large is the download?

A few hundred megabytes for the app. The models download once from inside it: about 1.7 GB for AI speech recognition plus the Chinese and English voices, and 150–250 MB more for Russian if you use it.

What do I need to run it?

Windows 10/11 (64-bit), or macOS 12 and newer with separate Apple silicon and Intel builds. 8 GB of RAM and four cores minimum; no GPU.

What if I change computers?

A code binds to one machine. Ask for a replacement after moving or reinstalling and the remaining credits come with it, free.

Who owns the material I import?

You do, and you are responsible for it. The app uploads nothing, distributes nothing and ships with no material of its own.

Can I get a refund?

Yes. Ask within 7 days of the charge and it is approved, no reason required — unused credits come back in full.

Five minutes of audio in. A finished lesson out.

Try it free first →

Windows & macOS · Instant delivery by email · Credits don't expire · 7-day refund