Speak. It lands in the right field.

Generic dictation tools transcribe speech to text and stop there. AI Dictation goes further: speech recognition transcribes, then the routing AI maps every sentence to the correct RICS field (D2 Roof Coverings, F1 Consumer Unit, B priority items), infers a condition rating, attaches a 0–1 confidence score and stores the audio so you can replay it for any field if questioned months later.

Record audio offline on your phone, then upload when you're back in coverage. Transcription and routing both run server-side once the audio is uploaded — you don't need to be on-site or online during processing.

Yes. The speech recognition handles a wide range of UK and international English accents reliably. If a word transcribes incorrectly, you can edit the transcript and re-route that sentence, or correct the text directly in the report editor.

Every observation you dictate creates a layered record: the audio file, the transcript sentence, the RICS field it was routed to, the condition rating inferred and the confidence score you reviewed. Months after a survey is delivered — when a PI challenge arrives — open the dictation panel, locate the relevant element and play back exactly what you said during the inspection. The record shows the AI's routing proposal separately from your sign-off, so you can demonstrate that every condition rating reflected your professional judgement. Most surveyors retain session audio for the duration of their PI cover period.

The AI flags low-confidence routings rather than silently absorbing unmatched content. You can move the text to a different field, attach it to a general section (B, C), or delete it. Nothing is automatically written to the report without your approval.

Both. In manual mode you use it directly inside the Level 2 or Level 3 editor to add observations to specific fields one session at a time. In Otto auto-mode the whole transcript is routed at once by our AI engine, populating all report sections in a single pass.

Accuracy depends on transcription clarity and how specifically you refer to building elements. Every route has a 0–1 confidence score: high-confidence routes (above ~0.85) typically need no review; low-confidence routes are flagged. Injecting your style profile and standard phrases consistently raises accuracy by giving the AI firm-specific vocabulary to match against.

If your firm uses a scale other than C1/C2/C3 — for example a 1–5 numeric scale or bespoke labels — you configure rating options in firm settings. AI Dictation runs a keyword-generation step that analyses each rating's description and produces synonyms, phrases and context hints, then rebuilds the routing prompt dynamically so the AI infers the correct custom rating from your spoken observations.

Audio files, transcripts and routed field updates are stored in secure cloud storage under your Home.co.uk surveyor account. You control retention: delete any dictation session from the panel to remove the audio and transcript permanently. Your survey content is used solely to deliver the routing service — it is never used to train AI models. Full data-handling details are in your account Data Processing Agreement.

Yes. The routing engine uses the same D–G element structure for both Level 2 and Level 3 reports. When you dictate into a Level 3 report, each observation is still routed to D1–D9, E1–E9, F1–F7 and G1–G3 in the same way. The Level 3 editor then provides the deeper commentary fields for each element — so your dictation populates the same field targets, and you expand the detail in the editor rather than re-dictating.

Most common audio and video formats are accepted — including MP3, MP4, M4A, WAV, WebM and OGG. If you record on a standard smartphone voice recorder or a dictaphone, the output format is almost certainly supported. You can also use the built-in browser microphone directly in the dictation panel without recording a file at all.

Five things matter most. First: RICS-native field mapping — the software should know that describing a chimney means D1, not just transcribe the word. Second: condition rating inference, so you don't have to say "rating two" explicitly. Third: replayable audio per field for your PI audit trail, not just a single unlinked recording. Fourth: style profile and standard phrases injection so every report sounds like your firm rather than generic survey-speak. Fifth: a confidence scoring system so you focus review time on uncertain routes rather than re-reading every line. AI Dictation on Home.co.uk provides all five as standard, embedded directly inside the RICS report editor.

Both. You can paste typed site notes directly into the dictation panel and route them exactly as you would a voice transcript. This is useful if you already use a shorthand note system on-site, or if you want to combine a brief voice recording with additional typed observations made after the survey. The routing AI treats typed input identically to a voice transcript — RICS field mapping, condition rating inference and confidence scoring all apply.

Yes. The dictation panel works in any modern mobile browser — no dedicated app required. You can record directly through the browser microphone, or use your phone's built-in voice recorder and upload the file when you're done. Most surveyors either record live through the browser on-site, or record offline with their phone's default voice app and upload the file on the drive home. Both workflows route identically — the transcript, routing and confidence scores are all produced from the uploaded audio.

Speech recognition is optimised for real-world environments. Wind, traffic and ambient site noise are common and handled well. If specific words are garbled by noise, the transcript displays those segments clearly so you can correct them before routing. The most effective measure is positioning the microphone closer to your mouth — an earphone with a built-in mic significantly improves accuracy in noisy conditions. If a segment transcribes poorly, you can edit the transcript text directly and re-route that sentence without re-recording the whole session.

AI Dictation is purpose-built for the RICS Home Survey Standard element structure used in Level 2 and Level 3 reports, but surveyors also use it to capture defect observations on new-build inspections. For structured new-build snagging — with a defect list by room, severity categories and client-facing output — the dedicated snagging report tool on Home.co.uk is the better starting point. The two tools complement each other: dictate your on-site observations quickly with AI Dictation, then use the snagging tool for the structured defect list presentation.

AI Dictation populates the condition and commentary sections of a RICS report from your on-site observations. Once routing is complete, the other tools in your Home.co.uk surveyor account add supporting data: the property data tool pulls the EPC rating, floor area, UPRN, flood risk zone and planning history for the inspected address; the comparable sales tool finds similar settled sales within your chosen radius. All three tools share the same report — no need to re-enter the address or switch between systems.

Yes. All audio files, transcripts and routed field updates are stored in secure cloud storage under your Home.co.uk surveyor account. No third party has access to your survey content. Audio is processed solely to deliver transcription and RICS field routing — it is never used to train AI models. You control retention: delete any dictation session from the panel at any time to remove the audio and transcript permanently. Your survey data is never shared outside your account. Full data-handling details, including your rights as a data subject, are in your account Data Processing Agreement.

Transcription and field routing typically complete within one to three minutes for a standard on-site recording of up to one hour. You can close the browser after uploading — you will be notified when routing is complete and your field updates are ready to review. For very long recordings over 90 minutes, splitting into two sessions before uploading can reduce processing time and also creates a more granular per-session audit trail for PI purposes.