Should you build your own ekto?
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 weekend 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.
ENOriginal research content in English. Original prompt preserved in English.
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.The prompt opens pre-filled in your agent. Review it before running. · this prompt is generated from the build plan · improve it via PR
What would building your own look like?
Streams mic audio over a WebSocket to a local Whisper plus translation plus TTS chain and plays the translated speech back with running transcript.
What you will need
- 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
- A browser with mic permission, or an API key if you swap in a hosted translation model
- Headphones, otherwise the TTS output feeds back into the mic
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.
xLong session reliability: memory growth, drifting segmentation and dropped turns after the first 20 minutes
xClean sentence by sentence pacing and turn detection, which is most of the perceived quality
xA mobile app, so no translating anything while standing up
xOffline or low-bandwidth behavior tuned for actual travel
xLatency budgets someone else already fought for: streaming partial results instead of waiting for a full segment
Nothing worth pointing at. That’s why the prompt exists.
How much does ekto cost?
- Monthly billing
- $34.99/mo$34.99/mo
- Per year
- $420/yr$420/yr
- On a Brazilian card, with 3.5% IOF
- R$183/moR$2,194/yr
Saved to My list. You will see a notice on this site when the price changes.
You complete the purchase on ekto’s site. Vibe Radar does not handle payments.
Is it cheaper to build or buy ekto?
Adjust the numbers: hours to build, your hourly rate, running costs and the subscription price.
Over 24 months, subscribing is cheaper.
Starting hours estimated from the analysis (a weekend). Does not price what you give up (support, integrations, security).
Can I rebuild ekto?
Kinda. The core of ekto is buildable in a weekend with the prompt on this page, but there are real gaps: 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. Read the honest list above before committing.
How much does ekto cost?
ekto costs about $34.99/mo (Monthly, checked 10/20/2026), which is $420 per year.
What do I lose by replacing ekto?
Honestly: 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. If any of those are load-bearing for you, keep paying.
Is there an open-source alternative to ekto?
No mature open-source alternative worth pointing at, which is exactly why the one-shot prompt on this page exists.