From 23cd63dcdb948af7f440d9802c3a517a0312c124 Mon Sep 17 00:00:00 2001 From: Georgios Hadjiharalambous Date: Mon, 13 Jul 2026 16:08:48 +0100 Subject: [PATCH 1/6] docs change for new languages support for disfleuncy --- docs/speech-to-text/formatting.mdx | 33 +++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/docs/speech-to-text/formatting.mdx b/docs/speech-to-text/formatting.mdx index a585e9ce..61e725d2 100644 --- a/docs/speech-to-text/formatting.mdx +++ b/docs/speech-to-text/formatting.mdx @@ -78,7 +78,7 @@ For other languages, consider using [word replacement](#word-replacement) to ide ## Disfluencies -Disfluencies are hesitation sounds like "um", "uh", and "hmm". In English, these are automatically tagged with `disfluency`: +Disfluencies are hesitation sounds like "um", "uh", and "hmm". Speechmatics automatically tags them with `disfluency` in the transcript output: ```json "results": [ @@ -101,7 +101,7 @@ Disfluencies are hesitation sounds like "um", "uh", and "hmm". In English, these ```
- Full list of tagged disfluencies + Full list of tagged English disfluencies {`huh aha @@ -147,6 +147,33 @@ uum`}
+### Supported languages + +Disfluency tagging and removal are available for the following languages. Each language has its own set of hesitation sounds; the full list above is for English. + +- Arabic +- Chinese Mandarin +- Danish +- Dutch +- English +- Finnish +- French +- German +- Greek +- Hebrew +- Hindi +- Hungarian +- Italian +- Japanese +- Norwegian +- Polish +- Portuguese +- Russian +- Spanish +- Swedish + +Coverage of hesitation sounds varies by language. If you rely on disfluency removal for a specific language, test it with representative audio rather than assuming full coverage. + ### Removing disfluencies You can automatically remove disfluencies from your transcript: @@ -169,7 +196,7 @@ Without disfluency removal: With disfluency removal: > What would you like? -This feature is available for English only. The default setting is `"remove_disfluencies": false`. +This feature is available for the [supported languages](#supported-languages). The default setting is `"remove_disfluencies": false`. ## Word replacement From 1f6f8e443aeebec610ac117778aa2d886c1fae74 Mon Sep 17 00:00:00 2001 From: Georgios Hadjiharalambous Date: Tue, 21 Jul 2026 13:30:25 +0100 Subject: [PATCH 2/6] put lang code --- docs/speech-to-text/formatting.mdx | 40 +++++++++++++++--------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/docs/speech-to-text/formatting.mdx b/docs/speech-to-text/formatting.mdx index 61e725d2..b288bdcc 100644 --- a/docs/speech-to-text/formatting.mdx +++ b/docs/speech-to-text/formatting.mdx @@ -151,26 +151,26 @@ uum`} Disfluency tagging and removal are available for the following languages. Each language has its own set of hesitation sounds; the full list above is for English. -- Arabic -- Chinese Mandarin -- Danish -- Dutch -- English -- Finnish -- French -- German -- Greek -- Hebrew -- Hindi -- Hungarian -- Italian -- Japanese -- Norwegian -- Polish -- Portuguese -- Russian -- Spanish -- Swedish +- Arabic (`ar`) +- Chinese Mandarin (`cmn`) +- Danish (`da`) +- Dutch (`nl`) +- English (`en`) +- Finnish (`fi`) +- French (`fr`) +- German (`de`) +- Greek (`el`) +- Hebrew (`he`) +- Hindi (`hi`) +- Hungarian (`hu`) +- Italian (`it`) +- Japanese (`ja`) +- Norwegian (`no`) +- Polish (`pl`) +- Portuguese (`pt`) +- Russian (`ru`) +- Spanish (`es`) +- Swedish (`sv`) Coverage of hesitation sounds varies by language. If you rely on disfluency removal for a specific language, test it with representative audio rather than assuming full coverage. From c21d150a2e8d766a5fe4356ae197e23c53b79ff5 Mon Sep 17 00:00:00 2001 From: Georgios Hadjiharalambous Date: Tue, 21 Jul 2026 16:31:04 +0100 Subject: [PATCH 3/6] MR review comments --- docs/speech-to-text/formatting.mdx | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/speech-to-text/formatting.mdx b/docs/speech-to-text/formatting.mdx index b288bdcc..7bd982bd 100644 --- a/docs/speech-to-text/formatting.mdx +++ b/docs/speech-to-text/formatting.mdx @@ -147,9 +147,9 @@ uum`} -### Supported languages +### Supported languages for disfluencies -Disfluency tagging and removal are available for the following languages. Each language has its own set of hesitation sounds; the full list above is for English. +Disfluency tagging and removal are available for the following languages. Each language has its own set of hesitation sounds; the expandable list at the start of this section covers English. - Arabic (`ar`) - Chinese Mandarin (`cmn`) @@ -196,7 +196,7 @@ Without disfluency removal: With disfluency removal: > What would you like? -This feature is available for the [supported languages](#supported-languages). The default setting is `"remove_disfluencies": false`. +This feature is available for the [supported languages](#supported-languages-for-disfluencies). The default setting is `"remove_disfluencies": false`. ## Word replacement @@ -368,7 +368,7 @@ The system applies different formatting rules based on the type of entity detect The system chooses entity classes based on context, so occasionally a value might be classified differently than expected. For example, "2001" could be a "cardinal" number or a "date". ::: -### Languages +### Languages for smart formatting Each language follows its own conventions for: From a06d9647a0583647f38c07845ca570f66cc59802 Mon Sep 17 00:00:00 2001 From: Georgios Hadjiharalambous Date: Tue, 21 Jul 2026 18:29:02 +0100 Subject: [PATCH 4/6] update spec too --- spec/realtime.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spec/realtime.yaml b/spec/realtime.yaml index db9490c8..53bd0887 100644 --- a/spec/realtime.yaml +++ b/spec/realtime.yaml @@ -1127,7 +1127,7 @@ components: tags: type: array description: | - This is a set list of profanities and disfluencies respectively that cannot be altered by the end user. `[disfluency]` is only present in English, and `[profanity]` is present in English, Spanish, and Italian + This is a set list of profanities and disfluencies respectively that cannot be altered by the end user. `[disfluency]` is present in the [supported languages](https://docs.speechmatics.com/speech-to-text/formatting#supported-languages-for-disfluencies), and `[profanity]` is present in English, Spanish, and Italian items: $ref: "#/components/schemas/RecognitionAlternativeTagsEnum" required: From 8526c2f45e1ebd55503124c442e64de09afc5905 Mon Sep 17 00:00:00 2001 From: Georgios Hadjiharalambous Date: Tue, 21 Jul 2026 21:03:05 +0100 Subject: [PATCH 5/6] change another ref I saw --- docs/private/voice-agent-api.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/private/voice-agent-api.mdx b/docs/private/voice-agent-api.mdx index 0ec355a7..587b33e2 100644 --- a/docs/private/voice-agent-api.mdx +++ b/docs/private/voice-agent-api.mdx @@ -41,7 +41,7 @@ Adapts to each speaker's pace over the course of a conversation. It adjusts the **Best for:** General conversational voice agents. -**Languages:** All supported languages. Disfluency detection is English-only — other languages fall back to speech-rate adaptation. +**Languages:** All supported languages. Disfluency detection is supported for [supported languages](https://docs.speechmatics.com/speech-to-text/formatting#supported-languages-for-disfluencies) — other languages fall back to speech-rate adaptation. **Trade-off:** Latency varies by speaker. From 682c3dcaa05158479369fe7dd727e741c950d415 Mon Sep 17 00:00:00 2001 From: Georgios Hadjiharalambous Date: Wed, 22 Jul 2026 13:25:32 +0100 Subject: [PATCH 6/6] improve readability --- docs/private/voice-agent-api.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/private/voice-agent-api.mdx b/docs/private/voice-agent-api.mdx index 587b33e2..2926052c 100644 --- a/docs/private/voice-agent-api.mdx +++ b/docs/private/voice-agent-api.mdx @@ -41,7 +41,7 @@ Adapts to each speaker's pace over the course of a conversation. It adjusts the **Best for:** General conversational voice agents. -**Languages:** All supported languages. Disfluency detection is supported for [supported languages](https://docs.speechmatics.com/speech-to-text/formatting#supported-languages-for-disfluencies) — other languages fall back to speech-rate adaptation. +**Languages:** All supported languages. Disfluency detection is available for the [supported languages](https://docs.speechmatics.com/speech-to-text/formatting#supported-languages-for-disfluencies) — other languages fall back to speech-rate adaptation. **Trade-off:** Latency varies by speaker.