From 80d59536b28a40b259b691bef8810e0cf2b8cab6 Mon Sep 17 00:00:00 2001
From: "rosetta-livekit-bot[bot]"
 <282703043+rosetta-livekit-bot[bot]@users.noreply.github.com>
Date: Thu, 18 Jun 2026 23:24:44 +0000
Subject: [PATCH] feat(soniox): support stt-rt-v5 endpoint sensitivity

---
 .changeset/fresh-otters-share.md               |  5 +++++
 plugins/soniox/etc/agents-plugin-soniox.api.md |  1 +
 plugins/soniox/src/stt.ts                      | 12 ++++++++++--
 3 files changed, 16 insertions(+), 2 deletions(-)
 create mode 100644 .changeset/fresh-otters-share.md

diff --git a/.changeset/fresh-otters-share.md b/.changeset/fresh-otters-share.md
new file mode 100644
index 000000000..e12371dd3
--- /dev/null
+++ b/.changeset/fresh-otters-share.md
@@ -0,0 +1,5 @@
+---
+"@livekit/agents-plugin-soniox": minor
+---
+
+Support Soniox stt-rt-v5 and endpointSensitivity.
diff --git a/plugins/soniox/etc/agents-plugin-soniox.api.md b/plugins/soniox/etc/agents-plugin-soniox.api.md
index 92bc97f76..202e6308a 100644
--- a/plugins/soniox/etc/agents-plugin-soniox.api.md
+++ b/plugins/soniox/etc/agents-plugin-soniox.api.md
@@ -72,6 +72,7 @@ export interface STTOptions {
     enableLanguageIdentification: boolean;
     // (undocumented)
     enableSpeakerDiarization: boolean;
+    endpointSensitivity?: number;
     // (undocumented)
     languageHints?: string[];
     // (undocumented)
diff --git a/plugins/soniox/src/stt.ts b/plugins/soniox/src/stt.ts
index b26c9cf76..3627c82c0 100644
--- a/plugins/soniox/src/stt.ts
+++ b/plugins/soniox/src/stt.ts
@@ -74,6 +74,8 @@ export interface STTOptions {
   enableLanguageIdentification: boolean;
   /** Maximum delay in milliseconds between speech cessation and endpoint detection. */
   maxEndpointDelayMs: number;
+  /** How readily the model emits speech endpoints. Range: -1.0 to 1.0. */
+  endpointSensitivity?: number;
   clientReferenceId?: string;
   translation?: TranslationConfig;
 }
@@ -81,13 +83,13 @@ export interface STTOptions {
 const defaultSTTOptions: STTOptions = {
   apiKey: process.env.SONIOX_API_KEY,
   baseUrl: BASE_URL,
-  model: 'stt-rt-v4',
+  model: 'stt-rt-v5',
   languageHintsStrict: false,
   numChannels: 1,
   sampleRate: 16000,
   enableSpeakerDiarization: false,
   enableLanguageIdentification: true,
-  maxEndpointDelayMs: 500,
+  maxEndpointDelayMs: 2000,
 };
 
 /** @public */
@@ -103,6 +105,11 @@ export class STT extends stt.STT {
     if (merged.maxEndpointDelayMs < 500 || merged.maxEndpointDelayMs > 3000) {
       throw new Error('maxEndpointDelayMs must be between 500 and 3000');
     }
+    if (merged.endpointSensitivity !== undefined) {
+      if (merged.endpointSensitivity < -1.0 || merged.endpointSensitivity > 1.0) {
+        throw new Error('endpointSensitivity must be between -1.0 and 1.0');
+      }
+    }
 
     super({
       streaming: true,
@@ -207,6 +214,7 @@ export class SpeechStream extends stt.SpeechStream {
       enable_language_identification: this.#opts.enableLanguageIdentification,
       client_reference_id: this.#opts.clientReferenceId,
       max_endpoint_delay_ms: this.#opts.maxEndpointDelayMs,
+      endpoint_sensitivity: this.#opts.endpointSensitivity,
     };
 
     if (this.#opts.translation) {