Other · au1Batch
Drop one real file in below and see what comes back — no account needed to watch it land. Everything this deployment accepts, and what Speechmatics publishes about it, is under the console.
Your audio, through Speechmatics Standard, now
Need the words as you speak, not after the file? Compare the providers live — same models, streaming, billed by the second.
Click or drag audio file here
Supports MP3, M4A, WAV, OGG
Up to 30 minutes of audio; longer recordings accepted up to 4 hours.
Enables raw parameter access for Speechmatics Standard (au1). Disables universal options.
Provides a hint for the minimum and maximum number of expected speakers to improve diarization accuracy.
Boosts the recognition probability of specific words or phrases, such as proper nouns or domain-specific terms. Provide one phrase per line.
What this deployment is
What it accepts
| Option | On this deployment |
|---|---|
| Speaker diarizationLabels who spoke when, so a two-person recording comes back as a conversation. | Yes |
| Speaker count hintTakes a minimum and maximum number of speakers to steer the labelling. | Yes |
| Custom vocabularyTakes a list of terms — product names, jargon — to bias recognition toward. | Yes |
| Automatic punctuationReturns punctuated, cased text rather than an unbroken lexical stream. | Yes |
| Smart formattingWrites numbers, dates and currency as a reader expects them: twenty dollars as $20. | No |
| Profanity filterMasks profane words in the returned transcript. | No |
What this deployment accepts through our API. A no means the option is not offered on this model here — not that the vendor has never shipped it.
Languages
59 languages on this deployment, as the vendor publishes them. It will also identify the language itself when you do not name one.
The vendor’s own parameters
| Parameter | Default | What it does |
|---|---|---|
diarization | unset | Separate speakers by voice, by audio channel, or both. Overrides the universal diarization switch. |
speaker_sensitivity | 0.5 | 0 to 1. Higher finds more distinct speakers, at the cost of splitting one voice in two. |
prefer_current_speaker | unset | Stay with the previous speaker when the acoustic match is close. Reduces false switches and can miss brief interjections. |
max_speakers | unset | Upper bound on distinct speakers. Two or more; ignored below that. |
channel_diarization_labels | unset | Comma-separated names for the audio channels, in order — for example: Agent, Caller. |
output_locale | unset | Regional spelling of the transcript. Set automatically from the chosen language; override it here. |
punctuation_sensitivity | unset | 0 to 1. Higher produces more punctuation. |
permitted_marks | unset | Punctuation marks to allow, separated by spaces — for example: . , ? — or "all". A comma cannot be a separator here because it is one of the marks. Overrides the universal punctuation switch. |
remove_disfluencies | unset | Drop hesitation sounds such as 'um' and 'uh', adjusting capitalisation around them. |
enable_entities | unset | Return dates, money and similar as single items carrying both their spoken and written forms. |
domain | unset | A domain-specialised pack for the chosen language, such as finance or medical. Leave empty for the general model. |
Passed through untouched, spelled exactly as Speechmatics spells them. They are on the advanced panel of the console above.
The fare, and what it is worth
We have not read a published fare for this deployment, so there is nothing here we would stand behind. The rest of the sheet is on the comparison page, and Speechmatics states this one on its own pages. What we charge is on our pricing page.
What Speechmatics says about it
Speechmatics' faster tier. Feature-identical to Enhanced — same languages, diarization and custom dictionary — trading accuracy for speed.
Speechmatics Standard (au1) documentation · Every model and region we test · Compare all 11 on one file