Can ekto be vibe coded?
Real-time voice translation: speak in one language, get the other side rendered back in near real time.
The pipeline is no longer exotic: capture mic audio, segment it with a voice activity detector, transcribe with Whisper, translate, speak it back with a local TTS voice. An agent can wire that into a working local app in a focused implementation and it will genuinely translate a conversation. What it will not do out of the gate is stay graceful for an hour: chunk boundaries clip words, speaker turns bleed together, latency creeps as the buffer grows, and the sentence by sentence pacing that makes these apps usable in real conversation is a tuning problem, not a coding problem. You also get no phone app, which is where voice translation actually happens. Fine for a desk setup and travel prep, unconvincing when you are holding it out to a stranger in a market.
Jump to the build brief ↓Legacy-calibrated assessment
Checked Aug 2026
What you pay today, before any DIY hosting
low editorial confidence
Tracked separately from the pricing check
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Streams mic audio over a WebSocket to a local Whisper plus translation plus TTS chain and plays the translated speech back with running transcript.
- Turn supplied scripts into speech or avatars through documented model APIs.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- Long session reliability: memory growth, drifting segmentation and dropped turns after the first 20 minutes
- Clean sentence by sentence pacing and turn detection, which is most of the perceived quality
- A mobile app, so no translating anything while standing up
- Offline or low-bandwidth behavior tuned for actual travel
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
- Reliability at the vendor's scale is an operations problem, not a prompt.
Build, switch, or keep paying
Narrower, with trade-offs
Streams mic audio over a WebSocket to a local Whisper plus translation plus TTS chain and plays the translated speech back with running transcript.
Use the build brief ↓No checked option yet
Compare the prior art below or build only the workflow you need.
$29.99/mo
Because voice translation is judged entirely on the seconds between someone finishing a sentence and you hearing it, and on whether it still works on minute 40. A local build nails the demo and then frays: barge-in, background noise, two people talking over each other, the phone locking. Paying gets you a phone in your pocket that handles those cases without you adding VAD thresholds mid-conversation.
Visit ekto ↗Why people still pay
Because voice translation is judged entirely on the seconds between someone finishing a sentence and you hearing it, and on whether it still works on minute 40. A local build nails the demo and then frays: barge-in, background noise, two people talking over each other, the phone locking. Paying gets you a phone in your pocket that handles those cases without you adding VAD thresholds mid-conversation.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
Reliability at the vendor's scale is an operations problem, not a prompt.
Model quality and inference operations are part of the product.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to ekto
Context
ekto — Real-time voice translation: speak in one language, get the other side rendered back in near real time. It currently costs $29.99/mo.
The pipeline is no longer exotic: capture mic audio, segment it with a voice activity detector, transcribe with Whisper, translate, speak it back with a local TTS voice. An agent can wire that into a working local app in a focused implementation and it will genuinely translate a conversation. What it will not do out of the gate is stay graceful for an hour: chunk boundaries clip words, speaker turns bleed together, latency creeps as the buffer grows, and the sentence by sentence pacing that makes these apps usable in real conversation is a tuning problem, not a coding problem. You also get no phone app, which is where voice translation actually happens. Fine for a desk setup and travel prep, unconvincing when you are holding it out to a stranger in a market.
This brief describes a focused, single-operator replacement for the part of ekto that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Streams mic audio over a WebSocket to a local Whisper plus translation plus TTS chain and plays the translated speech back with running transcript.
Turn supplied scripts into speech or avatars through documented model APIs.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Python 3.11 and a machine with at least 8GB RAM, GPU strongly preferred.
Local model downloads: faster-whisper and a Piper voice per target language.
Headphones, otherwise the TTS output feeds back into the mic.
Data and integrations
A browser with mic permission, or an API key if you swap in a hosted translation model.
Each of these needs a real account, credential, or quota. Set them up before writing feature code.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build a local real-time voice translation app. No accounts, no cloud services, no telemetry.
Stack, non-negotiable:
Python 3.11 + FastAPI, served with uvicorn on port 8000.
One HTML page with vanilla JS, no framework, no build step.
Audio in: browser getUserMedia, 16kHz mono, streamed to the server over a WebSocket in 250ms PCM chunks.
Speech to text: faster-whisper (small model default, configurable via .env).
Segmentation: silero-vad or webrtcvad to detect end of utterance. Do not translate on fixed timers, translate on detected utterance boundaries.
Translation: argostranslate with locally installed language pairs.
Text to speech: piper, one voice per target language, downloaded on first run into ./models.
Behavior:
User picks source and target language in a dropdown before starting.
Press Start, speak, and on each detected utterance the server returns: original text, translated text, and a WAV of the translated speech. The page appends both lines to a running transcript and plays the audio.
Show live latency per utterance in ms in the corner. Be honest, measure end of speech to audio ready.
Handle overlap: if a new utterance arrives while audio is playing, queue it, never drop it.
Long session hygiene: cap the in-memory transcript at 500 lines, reset the whisper buffer after every utterance, log RSS every 60 seconds.
Out of scope, do not build: mobile app, user accounts, cloud sync, speaker diarization, a two-phone conversation mode.
Deliverables: main.py, static/index.html, static/app.js, requirements.txt, .env.example (WHISPER_MODEL, DEVICE, COMPUTE_TYPE), scripts/download_models.py, and a README with exact run steps plus one paragraph on where this degrades in sessions over 20 minutes.
Run it, speak a test sentence in English with Spanish as target, and paste the measured latency into the README.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
Long session reliability: memory growth, drifting segmentation and dropped turns after the first 20 minutes.
Clean sentence by sentence pacing and turn detection, which is most of the perceived quality.
A mobile app, so no translating anything while standing up.
Offline or low-bandwidth behavior tuned for actual travel.
Latency budgets someone else already fought for: streaming partial results instead of waiting for a full segment.
What you still own after launch
Secure credentials, rotate secrets, and handle provider rate limits.
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
Operational risk. The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: low. No reviewed project implementation is linked yet.
Generated by Can It Be Vibe Coded? · Full report: https://www.canitbevibecoded.com/ekto
You still own the product
- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Projects built from this idea
No reviewed implementation has been linked for ekto yet. A submission is evidence for review, not automatic proof that the whole product was replaced.
Built a version of ekto?Submit the project as evidence for this report.
Before you start
Can ekto be vibe coded?
Partly, if you narrow it. The pipeline is no longer exotic: capture mic audio, segment it with a voice activity detector, transcribe with Whisper, translate, speak it back with a local TTS voice. An agent can wire that into a working local app in a focused implementation and it will genuinely translate a conversation. What it will not do out of the gate is stay graceful for an hour: chunk boundaries clip words, speaker turns bleed together, latency creeps as the buffer grows, and the sentence by sentence pacing that makes these apps usable in real conversation is a tuning problem, not a coding problem. You also get no phone app, which is where voice translation actually happens. Fine for a desk setup and travel prep, unconvincing when you are holding it out to a stranger in a market.
What can an AI coding agent reproduce from ekto?
Streams mic audio over a WebSocket to a local Whisper plus translation plus TTS chain and plays the translated speech back with running transcript. Turn supplied scripts into speech or avatars through documented model APIs. A responsive interface with real empty, loading, success, and error states.
What will a DIY ekto replacement still be missing?
Long session reliability: memory growth, drifting segmentation and dropped turns after the first 20 minutes; Clean sentence by sentence pacing and turn detection, which is most of the perceived quality; A mobile app, so no translating anything while standing up; Offline or low-bandwidth behavior tuned for actual travel; The last 20 percent is sync, migration fidelity, speed, and edge cases.; Reliability at the vendor's scale is an operations problem, not a prompt.
What do I still own after building a ekto alternative?
Secure credentials, rotate secrets, and handle provider rate limits. Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.