From 4ee5681d4542df859209cc79114dc22dba0196c9 Mon Sep 17 00:00:00 2001 From: rakeshv Date: Fri, 31 Jul 2026 15:11:04 +0530 Subject: [PATCH 1/7] Add private Realtime preview docs for next-gen model (melia-1) Document the Melia 1 Realtime preview for existing customers: dedicated preview endpoint, minimal StartRecognition config, partials, channel diarization, word-level language labelling, and the new LanguageInfo message. Cross-link from the Batch preview page. Co-Authored-By: Claude Opus 4.8 (1M context) --- docs/private/next-gen-model-realtime.mdx | 116 +++++++++++++++++++++++ docs/private/next-gen-model.mdx | 2 +- 2 files changed, 117 insertions(+), 1 deletion(-) create mode 100644 docs/private/next-gen-model-realtime.mdx diff --git a/docs/private/next-gen-model-realtime.mdx b/docs/private/next-gen-model-realtime.mdx new file mode 100644 index 00000000..31a2ee27 --- /dev/null +++ b/docs/private/next-gen-model-realtime.mdx @@ -0,0 +1,116 @@ +--- +description: Get started with our next-generation model for Realtime transcription +--- + +# Next-generation Model – Realtime + +## Introduction +We are offering existing customers an early preview of our next-generation model, `melia-1`, for Realtime transcription. This is the Realtime companion to the [Batch preview](./next-gen-model). + +:::warning +This is an early preview for evaluation only, and is not intended for production use. Only a subset of Realtime features is currently supported (see [Capabilities](#capabilities)). Remaining features will be added over time. +::: + +This page describes how to access the preview and what to expect in terms of capabilities. + +## Getting started +You can start right away using your existing API keys, no new credentials needed. If you don't have an API key, head to the [Portal](https://portal.speechmatics.com) to get one. + +## API reference +The API schema is consistent with the [V2 Realtime WebSocket API](https://docs.speechmatics.com/api-ref/realtime-transcription-websocket) with some additions and limitations described below. + +### Supported endpoint +The preview runs on a dedicated endpoint, separate from the production Realtime service: + +| Region | Endpoint | +| ------ | -------- | +| Preview (EU & US) | **wss://preview.rt.speechmatics.com/v2** | + +The preview is deployed in AWS France (EU) and Oregon (USA). + +### Minimal example +Example minimal `StartRecognition` message: + +```json +{ + "message": "StartRecognition", + "transcription_config": { + // highlight-start + "language": "multi", + "model": "melia-1" + // highlight-end + } +} +``` + +:::note +There is no `max_delay` or `max_delay_mode` in the preview. Final transcript latency is governed by the model's internal chunk length; there is no client-side setting to trade latency for accuracy yet. +::: + +### Partial transcripts +[Partials](/speech-to-text/realtime/output#partial-transcripts) are supported. Enable them with `enable_partials` in the `StartRecognition` message: + +```json +{ + "message": "StartRecognition", + "transcription_config": { + "language": "multi", + "model": "melia-1", + // highlight-start + "enable_partials": true + // highlight-end + } +} +``` + +### Channel diarization +[Channel diarization](/speech-to-text/realtime/realtime-diarization) is supported for multi-channel audio. Speaker diarization is not yet supported. + +### Language labelling +Each word in the transcript output carries a `language` property with the predicted language code. The model predicts the language being spoken at the word level. + +### LanguageInfo message +A new `LanguageInfo` message is sent from the transcriber to the client the first time a new language code is detected in the audio. It is emitted **once per language code**, immediately before that language first appears in an `AddTranscript` (Final) or `AddPartialTranscript` (Partial) message. + +Use it to configure how you process and display the transcript — for example, word spacing and text direction for right-to-left scripts. + +```json +{ + "message": "LanguageInfo", + "language": "ar", + "word_delimiter": " ", + "writing_direction": "right-to-left", + "partial": true +} +``` + +- `language` (String): The detected language code. +- `word_delimiter` (String): The delimiter to use between words when reconstructing the transcript for this language. +- `writing_direction` (String): Either `left-to-right` or `right-to-left`. +- `partial` (Boolean): Optional. When present, this is `true`, indicating the message was triggered by a Partial transcript. + +## Capabilities + +| Feature | Current capability | Future plans | +| ------- | ------------------ | ------------ | +| Transcription | ✅ Basic Realtime transcription | Ongoing improvements | +| Languages | ✅ All languages via `"language": "multi"` | | +| Partials | ✅ Supported | | +| Channel diarization | ✅ Supported | | +| Punctuation | ✅ Supported | | +| Output locale | ✅ Supported | | +| Language labelling | ✅ Word-level | | +| Speaker diarization | ⚠️ Not available | Prioritised according to customer need | +| Speaker identification | ⚠️ Not available | Prioritised according to customer need | +| Language hints | ⚠️ Not available | Prioritised according to customer need | +| `max_delay` / `max_delay_mode` | ⚠️ Not available | Under consideration | +| Mid-session config (`SetRecognitionConfig`) | ⚠️ Not available | Prioritised according to customer need | +| End of Utterance (EOU / FEOU) | ⚠️ Not available | Prioritised according to customer need | +| Custom dictionary | ⚠️ Not available | Prioritised according to customer need | +| Alphanumerics | ⚠️ Verbalised form only | Prioritised according to customer need | +| Entities / punctuation overrides | ⚠️ Not available | Prioritised according to customer need | +| Disfluency removal | ⚠️ Not available | Prioritised according to customer need | +| Profanity tagging | ⚠️ Not available | Prioritised according to customer need | +| Audio volume filtering | ⚠️ Not available | Prioritised according to customer need | +| Translation | ⚠️ Not available | Prioritised according to customer need | +| Audio events | ⚠️ Not available | Prioritised according to customer need | diff --git a/docs/private/next-gen-model.mdx b/docs/private/next-gen-model.mdx index 31c9e8ac..1e87efa3 100644 --- a/docs/private/next-gen-model.mdx +++ b/docs/private/next-gen-model.mdx @@ -6,7 +6,7 @@ description: Get started with our next-generation model ## Introduction We are excited to offer early access to our next-generation model, codenamed Omni. This new architecture is designed to provide improved multilingual capabilities, faster turnaround time and improved alphanumeric accuracy across all supported languages. -Currently available for Batch transcription, the Omni model will be made available for Realtime transcription in Q3 2026. +Currently available for Batch transcription, with a Realtime preview also available for existing customers — see [Next-generation Model – Realtime](./next-gen-model-realtime). This page will guide you through how to access the new model, and what to expect in terms of capabilities. From 45829277c63b04aab6206dc5e68f8fb5b92dde82 Mon Sep 17 00:00:00 2001 From: rakeshv Date: Fri, 31 Jul 2026 15:17:26 +0530 Subject: [PATCH 2/7] Trim RT preview docs to LanguageInfo-only reference and emoji capabilities Remove the Partials, Channel diarization, and Language labelling subsections so the API reference covers only the LanguageInfo message. Simplify the capabilities table: drop Transcription and Punctuation rows, remove the Future plans column, and use emoji-only support status. Co-Authored-By: Claude Opus 4.8 (1M context) --- docs/private/next-gen-model-realtime.mdx | 70 ++++++++---------------- 1 file changed, 23 insertions(+), 47 deletions(-) diff --git a/docs/private/next-gen-model-realtime.mdx b/docs/private/next-gen-model-realtime.mdx index 31a2ee27..78c1da1d 100644 --- a/docs/private/next-gen-model-realtime.mdx +++ b/docs/private/next-gen-model-realtime.mdx @@ -22,8 +22,8 @@ The API schema is consistent with the [V2 Realtime WebSocket API](https://docs.s ### Supported endpoint The preview runs on a dedicated endpoint, separate from the production Realtime service: -| Region | Endpoint | -| ------ | -------- | +| Region | Endpoint | +|-------------------|------------------------------------------| | Preview (EU & US) | **wss://preview.rt.speechmatics.com/v2** | The preview is deployed in AWS France (EU) and Oregon (USA). @@ -47,28 +47,6 @@ Example minimal `StartRecognition` message: There is no `max_delay` or `max_delay_mode` in the preview. Final transcript latency is governed by the model's internal chunk length; there is no client-side setting to trade latency for accuracy yet. ::: -### Partial transcripts -[Partials](/speech-to-text/realtime/output#partial-transcripts) are supported. Enable them with `enable_partials` in the `StartRecognition` message: - -```json -{ - "message": "StartRecognition", - "transcription_config": { - "language": "multi", - "model": "melia-1", - // highlight-start - "enable_partials": true - // highlight-end - } -} -``` - -### Channel diarization -[Channel diarization](/speech-to-text/realtime/realtime-diarization) is supported for multi-channel audio. Speaker diarization is not yet supported. - -### Language labelling -Each word in the transcript output carries a `language` property with the predicted language code. The model predicts the language being spoken at the word level. - ### LanguageInfo message A new `LanguageInfo` message is sent from the transcriber to the client the first time a new language code is detected in the audio. It is emitted **once per language code**, immediately before that language first appears in an `AddTranscript` (Final) or `AddPartialTranscript` (Partial) message. @@ -91,26 +69,24 @@ Use it to configure how you process and display the transcript — for example, ## Capabilities -| Feature | Current capability | Future plans | -| ------- | ------------------ | ------------ | -| Transcription | ✅ Basic Realtime transcription | Ongoing improvements | -| Languages | ✅ All languages via `"language": "multi"` | | -| Partials | ✅ Supported | | -| Channel diarization | ✅ Supported | | -| Punctuation | ✅ Supported | | -| Output locale | ✅ Supported | | -| Language labelling | ✅ Word-level | | -| Speaker diarization | ⚠️ Not available | Prioritised according to customer need | -| Speaker identification | ⚠️ Not available | Prioritised according to customer need | -| Language hints | ⚠️ Not available | Prioritised according to customer need | -| `max_delay` / `max_delay_mode` | ⚠️ Not available | Under consideration | -| Mid-session config (`SetRecognitionConfig`) | ⚠️ Not available | Prioritised according to customer need | -| End of Utterance (EOU / FEOU) | ⚠️ Not available | Prioritised according to customer need | -| Custom dictionary | ⚠️ Not available | Prioritised according to customer need | -| Alphanumerics | ⚠️ Verbalised form only | Prioritised according to customer need | -| Entities / punctuation overrides | ⚠️ Not available | Prioritised according to customer need | -| Disfluency removal | ⚠️ Not available | Prioritised according to customer need | -| Profanity tagging | ⚠️ Not available | Prioritised according to customer need | -| Audio volume filtering | ⚠️ Not available | Prioritised according to customer need | -| Translation | ⚠️ Not available | Prioritised according to customer need | -| Audio events | ⚠️ Not available | Prioritised according to customer need | +| Feature | Supported | +|---------------------------------------------|-----------| +| Languages (`"language": "multi"`) | ✅ | +| Partials | ✅ | +| Channel diarization | ✅ | +| Output locale | ✅ | +| Language labelling (word-level) | ✅ | +| Speaker diarization | ⚠️ | +| Speaker identification | ⚠️ | +| Language hints | ⚠️ | +| `max_delay` / `max_delay_mode` | ⚠️ | +| Mid-session config (`SetRecognitionConfig`) | ⚠️ | +| End of Utterance (EOU / FEOU) | ⚠️ | +| Custom dictionary | ⚠️ | +| Alphanumerics (verbalised form only) | ⚠️ | +| Entities / punctuation overrides | ⚠️ | +| Disfluency removal | ⚠️ | +| Profanity tagging | ⚠️ | +| Audio volume filtering | ⚠️ | +| Translation | ⚠️ | +| Audio events | ⚠️ | From c58189f832f00817f9903560a130b8dd0af22253 Mon Sep 17 00:00:00 2001 From: rakeshv Date: Fri, 31 Jul 2026 15:20:04 +0530 Subject: [PATCH 3/7] Restore descriptive capabilities table with Future plans column Bring back the Current capability descriptions and the Future plans column, keeping Transcription and Punctuation out of the table. Co-Authored-By: Claude Opus 4.8 (1M context) --- docs/private/next-gen-model-realtime.mdx | 42 ++++++++++++------------ 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/docs/private/next-gen-model-realtime.mdx b/docs/private/next-gen-model-realtime.mdx index 78c1da1d..38307e13 100644 --- a/docs/private/next-gen-model-realtime.mdx +++ b/docs/private/next-gen-model-realtime.mdx @@ -69,24 +69,24 @@ Use it to configure how you process and display the transcript — for example, ## Capabilities -| Feature | Supported | -|---------------------------------------------|-----------| -| Languages (`"language": "multi"`) | ✅ | -| Partials | ✅ | -| Channel diarization | ✅ | -| Output locale | ✅ | -| Language labelling (word-level) | ✅ | -| Speaker diarization | ⚠️ | -| Speaker identification | ⚠️ | -| Language hints | ⚠️ | -| `max_delay` / `max_delay_mode` | ⚠️ | -| Mid-session config (`SetRecognitionConfig`) | ⚠️ | -| End of Utterance (EOU / FEOU) | ⚠️ | -| Custom dictionary | ⚠️ | -| Alphanumerics (verbalised form only) | ⚠️ | -| Entities / punctuation overrides | ⚠️ | -| Disfluency removal | ⚠️ | -| Profanity tagging | ⚠️ | -| Audio volume filtering | ⚠️ | -| Translation | ⚠️ | -| Audio events | ⚠️ | +| Feature | Current capability | Future plans | +|---------------------------------------------|-------------------------------------------|----------------------------------------| +| Languages | ✅ All languages via `"language": "multi"` | | +| Partials | ✅ Supported | | +| Channel diarization | ✅ Supported | | +| Output locale | ✅ Supported | | +| Language labelling | ✅ Word-level | | +| Speaker diarization | ⚠️ Not yet | Prioritised according to customer need | +| Speaker identification | ⚠️ Not yet | Prioritised according to customer need | +| Language hints | ⚠️ Not yet | Prioritised according to customer need | +| `max_delay` / `max_delay_mode` | ⚠️ Not yet | Under consideration | +| Mid-session config (`SetRecognitionConfig`) | ⚠️ Not yet | Prioritised according to customer need | +| End of Utterance (EOU / FEOU) | ⚠️ Not yet | Prioritised according to customer need | +| Custom dictionary | ⚠️ Not yet | Prioritised according to customer need | +| Alphanumerics | ⚠️ Verbalised form only | Prioritised according to customer need | +| Entities / punctuation overrides | ⚠️ Not yet | Prioritised according to customer need | +| Disfluency removal | ⚠️ Not yet | Prioritised according to customer need | +| Profanity tagging | ⚠️ Not yet | Prioritised according to customer need | +| Audio volume filtering | ⚠️ Not yet | Prioritised according to customer need | +| Translation | ⚠️ Not yet | Prioritised according to customer need | +| Audio events | ⚠️ Not yet | Prioritised according to customer need | From e3da93d96a15e3bd5f82c55e8eb7d574aa6ea390 Mon Sep 17 00:00:00 2001 From: rakeshv Date: Fri, 31 Jul 2026 16:54:30 +0530 Subject: [PATCH 4/7] Remove Languages row from RT capabilities table Co-Authored-By: Claude Opus 4.8 (1M context) --- docs/private/next-gen-model-realtime.mdx | 1 - 1 file changed, 1 deletion(-) diff --git a/docs/private/next-gen-model-realtime.mdx b/docs/private/next-gen-model-realtime.mdx index 38307e13..92a28f12 100644 --- a/docs/private/next-gen-model-realtime.mdx +++ b/docs/private/next-gen-model-realtime.mdx @@ -71,7 +71,6 @@ Use it to configure how you process and display the transcript — for example, | Feature | Current capability | Future plans | |---------------------------------------------|-------------------------------------------|----------------------------------------| -| Languages | ✅ All languages via `"language": "multi"` | | | Partials | ✅ Supported | | | Channel diarization | ✅ Supported | | | Output locale | ✅ Supported | | From 4a9359db68b1bff98aedca7b339456a50a20169d Mon Sep 17 00:00:00 2001 From: rakeshv Date: Fri, 31 Jul 2026 17:27:04 +0530 Subject: [PATCH 5/7] Add Word timings and use "Matches current behaviour" for supported features Co-Authored-By: Claude Opus 4.8 (1M context) --- docs/private/next-gen-model-realtime.mdx | 41 ++++++++++++------------ 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/docs/private/next-gen-model-realtime.mdx b/docs/private/next-gen-model-realtime.mdx index 92a28f12..58c3253e 100644 --- a/docs/private/next-gen-model-realtime.mdx +++ b/docs/private/next-gen-model-realtime.mdx @@ -69,23 +69,24 @@ Use it to configure how you process and display the transcript — for example, ## Capabilities -| Feature | Current capability | Future plans | -|---------------------------------------------|-------------------------------------------|----------------------------------------| -| Partials | ✅ Supported | | -| Channel diarization | ✅ Supported | | -| Output locale | ✅ Supported | | -| Language labelling | ✅ Word-level | | -| Speaker diarization | ⚠️ Not yet | Prioritised according to customer need | -| Speaker identification | ⚠️ Not yet | Prioritised according to customer need | -| Language hints | ⚠️ Not yet | Prioritised according to customer need | -| `max_delay` / `max_delay_mode` | ⚠️ Not yet | Under consideration | -| Mid-session config (`SetRecognitionConfig`) | ⚠️ Not yet | Prioritised according to customer need | -| End of Utterance (EOU / FEOU) | ⚠️ Not yet | Prioritised according to customer need | -| Custom dictionary | ⚠️ Not yet | Prioritised according to customer need | -| Alphanumerics | ⚠️ Verbalised form only | Prioritised according to customer need | -| Entities / punctuation overrides | ⚠️ Not yet | Prioritised according to customer need | -| Disfluency removal | ⚠️ Not yet | Prioritised according to customer need | -| Profanity tagging | ⚠️ Not yet | Prioritised according to customer need | -| Audio volume filtering | ⚠️ Not yet | Prioritised according to customer need | -| Translation | ⚠️ Not yet | Prioritised according to customer need | -| Audio events | ⚠️ Not yet | Prioritised according to customer need | +| Feature | Current capability | Future plans | +|---------------------------------------------|------------------------------|----------------------------------------| +| Partials | ✅ Matches current behaviour | | +| Channel diarization | ✅ Matches current behaviour | | +| Output locale | ✅ Matches current behaviour | | +| Word timings | ✅ Matches current behaviour | | +| Language labelling | ✅ Word-level | | +| Speaker diarization | ⚠️ Not yet | Prioritised according to customer need | +| Speaker identification | ⚠️ Not yet | Prioritised according to customer need | +| Language hints | ⚠️ Not yet | Prioritised according to customer need | +| `max_delay` / `max_delay_mode` | ⚠️ Not yet | Under consideration | +| Mid-session config (`SetRecognitionConfig`) | ⚠️ Not yet | Prioritised according to customer need | +| End of Utterance (EOU / FEOU) | ⚠️ Not yet | Prioritised according to customer need | +| Custom dictionary | ⚠️ Not yet | Prioritised according to customer need | +| Alphanumerics | ⚠️ Verbalised form only | Prioritised according to customer need | +| Entities / punctuation overrides | ⚠️ Not yet | Prioritised according to customer need | +| Disfluency removal | ⚠️ Not yet | Prioritised according to customer need | +| Profanity tagging | ⚠️ Not yet | Prioritised according to customer need | +| Audio volume filtering | ⚠️ Not yet | Prioritised according to customer need | +| Translation | ⚠️ Not yet | Prioritised according to customer need | +| Audio events | ⚠️ Not yet | Prioritised according to customer need | From 29e0c14b82f322758b0dcdcae7dcbb126932e895 Mon Sep 17 00:00:00 2001 From: rakeshv Date: Fri, 31 Jul 2026 17:33:19 +0530 Subject: [PATCH 6/7] private docs for melia-1 RT --- docs/private/next-gen-model-realtime.mdx | 38 +++++++++++------------- 1 file changed, 17 insertions(+), 21 deletions(-) diff --git a/docs/private/next-gen-model-realtime.mdx b/docs/private/next-gen-model-realtime.mdx index 58c3253e..4176992e 100644 --- a/docs/private/next-gen-model-realtime.mdx +++ b/docs/private/next-gen-model-realtime.mdx @@ -26,7 +26,7 @@ The preview runs on a dedicated endpoint, separate from the production Realtime |-------------------|------------------------------------------| | Preview (EU & US) | **wss://preview.rt.speechmatics.com/v2** | -The preview is deployed in AWS France (EU) and Oregon (USA). +The preview is deployed in France (EU) and Oregon (USA). ### Minimal example Example minimal `StartRecognition` message: @@ -43,10 +43,6 @@ Example minimal `StartRecognition` message: } ``` -:::note -There is no `max_delay` or `max_delay_mode` in the preview. Final transcript latency is governed by the model's internal chunk length; there is no client-side setting to trade latency for accuracy yet. -::: - ### LanguageInfo message A new `LanguageInfo` message is sent from the transcriber to the client the first time a new language code is detected in the audio. It is emitted **once per language code**, immediately before that language first appears in an `AddTranscript` (Final) or `AddPartialTranscript` (Partial) message. @@ -69,24 +65,24 @@ Use it to configure how you process and display the transcript — for example, ## Capabilities -| Feature | Current capability | Future plans | -|---------------------------------------------|------------------------------|----------------------------------------| +| Feature | Current capability | Future plans | +|---------------------------------------------|-----------------------------|----------------------------------------| | Partials | ✅ Matches current behaviour | | | Channel diarization | ✅ Matches current behaviour | | | Output locale | ✅ Matches current behaviour | | | Word timings | ✅ Matches current behaviour | | | Language labelling | ✅ Word-level | | -| Speaker diarization | ⚠️ Not yet | Prioritised according to customer need | -| Speaker identification | ⚠️ Not yet | Prioritised according to customer need | -| Language hints | ⚠️ Not yet | Prioritised according to customer need | -| `max_delay` / `max_delay_mode` | ⚠️ Not yet | Under consideration | -| Mid-session config (`SetRecognitionConfig`) | ⚠️ Not yet | Prioritised according to customer need | -| End of Utterance (EOU / FEOU) | ⚠️ Not yet | Prioritised according to customer need | -| Custom dictionary | ⚠️ Not yet | Prioritised according to customer need | -| Alphanumerics | ⚠️ Verbalised form only | Prioritised according to customer need | -| Entities / punctuation overrides | ⚠️ Not yet | Prioritised according to customer need | -| Disfluency removal | ⚠️ Not yet | Prioritised according to customer need | -| Profanity tagging | ⚠️ Not yet | Prioritised according to customer need | -| Audio volume filtering | ⚠️ Not yet | Prioritised according to customer need | -| Translation | ⚠️ Not yet | Prioritised according to customer need | -| Audio events | ⚠️ Not yet | Prioritised according to customer need | +| Speaker diarization | ⚠️ Not yet | Prioritised according to customer need | +| Speaker identification | ⚠️ Not yet | Prioritised according to customer need | +| Language hints | ⚠️ Not yet | Prioritised according to customer need | +| `max_delay` / `max_delay_mode` | ⚠️ Not yet | Under consideration | +| Mid-session config (`SetRecognitionConfig`) | ⚠️ Not yet | Prioritised according to customer need | +| End of Utterance (EOU / FEOU) | ⚠️ Not yet | Prioritised according to customer need | +| Custom dictionary | ⚠️ Not yet | Prioritised according to customer need | +| Alphanumerics | ⚠️ Not yet | Prioritised according to customer need | +| Entities / punctuation overrides | ⚠️ Not yet | Prioritised according to customer need | +| Disfluency removal | ⚠️ Not yet | Prioritised according to customer need | +| Profanity tagging | ⚠️ Not yet | Prioritised according to customer need | +| Audio volume filtering | ⚠️ Not yet | Prioritised according to customer need | +| Translation | ⚠️ Not yet | Prioritised according to customer need | +| Audio events | ⚠️ Not yet | Prioritised according to customer need | From 49a8c5e8af0a27c1d9eb35344c5f816b1317a1a5 Mon Sep 17 00:00:00 2001 From: rakeshv Date: Fri, 31 Jul 2026 17:35:36 +0530 Subject: [PATCH 7/7] update comment on model availability --- docs/private/next-gen-model.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/private/next-gen-model.mdx b/docs/private/next-gen-model.mdx index 1e87efa3..ec0a05fe 100644 --- a/docs/private/next-gen-model.mdx +++ b/docs/private/next-gen-model.mdx @@ -6,7 +6,7 @@ description: Get started with our next-generation model ## Introduction We are excited to offer early access to our next-generation model, codenamed Omni. This new architecture is designed to provide improved multilingual capabilities, faster turnaround time and improved alphanumeric accuracy across all supported languages. -Currently available for Batch transcription, with a Realtime preview also available for existing customers — see [Next-generation Model – Realtime](./next-gen-model-realtime). +Currently available for Batch transcription and Realtime transcription — see [Next-generation Model – Realtime](./next-gen-model-realtime). This page will guide you through how to access the new model, and what to expect in terms of capabilities.