Loquela RemoteSpeech-to-text that runs on hardware we own.
Send a finished recording and get the text back, with word timings and speaker labels when you want them. The audio stays in memory while it's transcribed, then it's erased. Nothing is kept, and nothing is used for training.
Loquela Remote is in open beta and close to release. Anyone who supports us during the beta gets early access to new models, free credits and more. Join the Founder program
memo.wav, 5.8 secondsanswered in 0.34 sRemind me to send a contract to Dana on Thursday, and book the small room for 10.
A real response with word timings, from a synthetic voice.
Three ways in
From your code
The API follows OpenAI's transcription format, so an OpenAI SDK works once you change the base URL.
From an AI assistant
Add the MCP server to Claude, ChatGPT, Cursor or your own agent, and it can transcribe links, clips and files.
In your browser
Sign in, drop in a file or record from your microphone, and get text or subtitles back.
What happens to a recording
It travels encrypted to our computer in North Carolina.
It's encrypted to your account's own PGP key before it leaves your computer.
It's held in memory and never saved.
Our computer opens it in memory, only for your request, and never saves it.
Our own hardware turns it into text.
Our own hardware turns it into text.
You get the text back, and the audio is erased.
The text comes back encrypted to your key and signed by us, and the audio is erased.
Why people pick it
- transcribe speed400×
- An hour of audio in under 9 seconds of server time, in our own tests (60-minute MP3 and AAC files, upload not counted).
- languages25
- English plus 24 European languages, for customers in the United States.
- recordings kept0
- For billing we keep one line per request: the time, the audio's length, the minutes charged and whether it worked.
- encryptionPGP
- On Pro and Business plans: send audio encrypted to your key and get the transcript back encrypted too.
What people use it for
Pricing
- Plans from $9.99 a month for 5,000 minutes, with 2 months free when you pay yearly.
- Or pay as you go at $0.0035 a minute.
- Enterprise rates for sustained, high-volume use start at $0.0012 a minute.
Questions
Do you store my audio or transcripts?
No. Audio and transcripts stay in memory and are erased when your request ends. For billing we keep one line per request: the time, the audio's length, the minutes charged and whether it worked.
Does it work with the OpenAI SDK?
Yes. Set the base URL to https://api.getloquela.com/v1 and use a Loquela Remote API key. Responses come as json, text, srt, vtt, verbose_json with word timings, or diarized_json with speakers.
Can I use it from Loquela Desktop or Android?
Yes. Loquela Desktop connects to Remote with an API key, and the Android app can send dictation to it through its third-party API key option.