AI glossary · Voice
Automatic transcription
In one sentence
Automatic transcription is the process of turning an audio or video recording into written text without anyone typing it, using speech recognition. It usually adds punctuation, timestamps and labels showing who is speaking at each point.
Also known as: AI transcription · audio to text transcription · machine transcription · call transcription
What is automatic transcription?
For years, getting a meeting or interview into text meant hours of listening, pausing and typing. Automatic transcription does the job in a fraction of the time. Underneath it uses speech recognition, but it doesn’t stop at pulling out words: it delivers a usable document.
Put it to work
UTIO's AI, through an API
From €29/mo + VAT
For developers and agencies building their own products.
See the AI APIWhat sets it apart from raw speech to text is what it adds:
- Punctuation and formatting, so it reads like prose rather than a string of words.
- Diarisation: separating who speaks when (“Agent:”, “Customer:”).
- Timestamps, so you can jump to the exact moment in the audio.
- Export to a document, to subtitles or straight into your CRM.
Other AI techniques can then work on the text: summarising, pulling out action points or spotting a customer’s tone. The transcript becomes the raw material for everything else.
Related to this term
AI API
- Transcription, voice, text, image, OCR and embeddings
- Per-client keys with a spending cap
- Prepaid wallet: €50 minimum top-up
From €29/mo + VAT Panel account, plus usage
See the AI APIHow it works
- Upload or capture the audio. A call recording, a voice note, a video.
- The language is detected and the audio cleaned up if needed.
- The recognition engine converts speech to text, usually in batch mode, which is more accurate because it sees the whole recording.
- Speakers are separated and the text formatted.
- The result is delivered as a file or, through an API, into whichever system needs it.
Example
A law firm in Liverpool records, with consent, its first consultations with clients. A trainee used to spend the afternoon typing them up. Now each recording is transcribed automatically, with solicitor and client separated, and the text goes into the case file. The trainee only checks names and dates, which is where the machine slips most. Searching for “exchange of contracts” across every consultation that month takes seconds.
Automatic transcription at UTIO
UTIO’s AI API includes transcription: calls and audio to text, with the language detected, using the same key as its other capabilities (text to speech, text, OCR, embeddings). Authentication is a header carrying your panel key, and each key has its own spending cap and rate limit.
If you simply want your company’s calls transcribed without writing code, the voice agent already saves a transcript of every call to the CRM, on servers in Spain.
Frequently asked questions
How accurate is automatic transcription?
With clean audio and a single speaker, current systems make few mistakes. Accuracy drops with background noise, people talking over each other, phone audio or very technical vocabulary. For legal or medical use, plan for a human review.
What is the difference between automatic transcription and speech to text?
Speech to text is the engine that turns voice into text. Automatic transcription is the finished result for a reader: the text of a recording, formatted, split by speaker and timestamped, ready to read, search or file.
Can I transcribe customer calls?
Yes, as long as you comply with GDPR: tell callers at the start that the call is recorded and why, keep recordings and transcripts only as long as needed, and sign a data-processing agreement with your provider.
Related terms
- Speech to text
Speech to text (STT) is the technology that turns spoken audio into written text. It's the software component, usually a model reached through an API, that does the listening in a voicebot, a dictation tool or a transcription service, either live or on recordings.
- Speech recognition
Speech recognition is the branch of artificial intelligence that lets a machine identify the words a person says and turn them into text or commands. Its technical name is ASR, short for automatic speech recognition.
- API
An API (application programming interface) is a set of rules that lets one program ask another for data or an action: you send a request in an agreed format and get a response back, without needing to know how the other system works inside.
- Sentiment analysis
Sentiment analysis is the AI technique that detects the emotional tone of a text (positive, negative or neutral, and sometimes emotions such as anger or urgency) so you know how the writer feels without reading everything by hand.
Updated on