stephenvapiai · Oct 14, 2026 · Oct 13, 2026
diff --git a/fern/assistants/examples/multilingual-agent.mdx b/fern/assistants/examples/multilingual-agent.mdx
@@ -328,7 +328,7 @@ The CSV files contain fictional example data for this tutorial. Do not call or e
         // Option 2: Google Multilingual
         const googleTranscriber = {
           provider: "google",
-          model: "gemini-2.0-flash",
+          model: "gemini-2.5-flash",
           language: "Multilingual"
         } as const;
 
@@ -354,7 +354,7 @@ The CSV files contain fictional example data for this tutorial. Do not call or e
         # Option 2: Google Multilingual
         google_transcriber = {
             "provider": "google",
-            "model": "gemini-2.0-flash",
+            "model": "gemini-2.5-flash",
             "language": "Multilingual"
         }
 
@@ -397,7 +397,7 @@ The CSV files contain fictional example data for this tutorial. Do not call or e
              -d '{
                "transcriber": {
                  "provider": "google",
-                 "model": "gemini-2.0-flash",
+                 "model": "gemini-2.5-flash",
                  "language": "Multilingual"
                }
              }'

diff --git a/fern/calls/call-ended-reason.mdx b/fern/calls/call-ended-reason.mdx
@@ -150,7 +150,7 @@ Common transcriber error patterns:
 - `*-returning-403-*` — Model access denied on the transcriber.
 - `*-returning-500-*` / `*-returning-502-*` — Transcriber provider server error.
 
-**Supported providers:** Deepgram, AssemblyAI, Gladia, Speechmatics, Talkscriber, Azure Speech, Google, OpenAI, Soniox, ElevenLabs, Custom Transcriber.
+**Supported providers:** Deepgram, AssemblyAI, Gladia, Speechmatics, Azure Speech, Google, OpenAI, Soniox, ElevenLabs, Custom Transcriber.
 
 ## Transfer errors
 

diff --git a/fern/customization/multilingual.mdx b/fern/customization/multilingual.mdx
@@ -53,7 +53,7 @@ Set up your transcriber to automatically detect and process multiple languages.
     // Alternative: Google for multilingual support
     const googleMultilingual = {
       provider: "google",
-      model: "gemini-2.0-flash",
+      model: "gemini-2.5-flash",
       language: "Multilingual"
     };
     ```
@@ -78,7 +78,7 @@ Set up your transcriber to automatically detect and process multiple languages.
     # Alternative: Google for multilingual support
     google_multilingual = {
         "provider": "google",
-        "model": "gemini-2.0-flash",
+        "model": "gemini-2.5-flash",
         "language": "Multilingual"
     }
     ```
@@ -105,7 +105,7 @@ Set up your transcriber to automatically detect and process multiple languages.
          -d '{
            "transcriber": {
              "provider": "google",
-             "model": "gemini-2.0-flash",
+             "model": "gemini-2.5-flash",
              "language": "Multilingual"
            }
          }'
@@ -488,7 +488,6 @@ Use [plan test coverage](/test/plan-test-coverage) to prioritize the languages a
 | **Azure STT** | ❌ Single language | 100+ | Many languages, but no auto-detection |
 | **OpenAI Whisper** | ❌ Single language | 90+ | Many languages, but no auto-detection |
 | **Speechmatics** | ❌ Single language | 50+ | Many languages, but no auto-detection |
-| **Talkscriber** | ❌ Single language | 40+ | Many languages, but no auto-detection |
 
 ### Voice Synthesis (Text-to-Speech)
 

diff --git a/fern/customization/transcriber-fallback-plan.mdx b/fern/customization/transcriber-fallback-plan.mdx
@@ -224,12 +224,6 @@ Each transcriber provider supports different configuration options. Expand a pro
     - **removeDisfluencies**: Removes disfluencies from English transcripts when enabled.
     - **minimumSpeechDuration**: Minimum speech-segment duration, from `0` to `5` seconds.
   </Accordion>
-  <Accordion title="Talkscriber">
-    - **model**: Talkscriber transcription model.
-    - **language**: Language code for transcription.
-
-    See [Talkscriber](/providers/transcriber/talkscriber) for the supported model and languages.
-  </Accordion>
   <Accordion title="xAI">
     - **model**: xAI transcription model.
     - **language**: Language code for transcription.

diff --git a/fern/docs.yml b/fern/docs.yml
@@ -831,8 +831,6 @@ navigation:
                     path: providers/transcriber/soniox.mdx
                   - page: Speechmatics
                     path: providers/transcriber/speechmatics.mdx
-                  - page: Talkscriber
-                    path: providers/transcriber/talkscriber.mdx
                   - page: xAI
                     path: providers/transcriber/xai.mdx
 
@@ -1142,6 +1140,8 @@ redirects:
     destination: /providers/voice/overview
   - source: /providers/voice/sesame
     destination: /providers/voice/overview
+  - source: /providers/transcriber/talkscriber
+    destination: /providers/transcriber/overview
   - source: /providers/gpt-live
     destination: /gpt-live/overview
   - source: /gpt-live/voices

diff --git a/fern/observability/evals-quickstart.mdx b/fern/observability/evals-quickstart.mdx
@@ -680,27 +680,23 @@ curl -X POST "https://api.vapi.ai/eval" \
 
 <CardGroup cols={2}>
   <Card title="OpenAI" icon="brain">
-    **Models:** gpt-4o, gpt-4-turbo, gpt-3.5-turbo
-    
+    **Models:** gpt-6-luna, gpt-5.6-sol
+
     Best for general-purpose evaluation
   </Card>
+  <Card title="Anthropic" icon="message-bot">
+    **Model:** claude-sonnet-5
 
-{" "}
-
-<Card title="Anthropic" icon="message-bot">
-  **Models:** claude-3-5-sonnet-20241022, claude-3-opus-20240229 Best for
-  nuanced evaluation
-</Card>
-
-{" "}
-
-<Card title="Google" icon="google">
-  **Models:** gemini-1.5-pro, gemini-1.5-flash Best for multilingual content
-</Card>
+    Best for nuanced evaluation
+  </Card>
+  <Card title="Google" icon="google">
+    **Model:** gemini-3.5-flash
 
+    Best for multilingual content
+  </Card>
   <Card title="Groq" icon="bolt">
-    **Models:** llama-3.1-70b-versatile, mixtral-8x7b-32768
-    
+    **Model:** openai/gpt-oss-120b
+
     Best for fast evaluation
   </Card>
 </CardGroup>

diff --git a/fern/providers/model/cerebras.mdx b/fern/providers/model/cerebras.mdx
@@ -1,7 +1,7 @@
 ---
 title: Cerebras
-subtitle: Connect your Cerebras account to use Cerebras models in Vapi
-description: Connect a Cerebras API key to Vapi and configure an assistant with a supported Cerebras model.
+subtitle: Connect your Cerebras account and configure any model available to it
+description: Connect a Cerebras API key to Vapi and configure an assistant with an exact model ID from your Cerebras account.
 slug: providers/model/cerebras
 ---
 
@@ -13,27 +13,26 @@ Cerebras serves open large language models on its own inference hardware, optimi
 
 ## Connect Cerebras
 
-Cerebras requires your own account. Connect your Cerebras API key on the [Integrations](/providers/integrations) page before configuring an assistant. Without a connected Cerebras key, the models below will not work.
+Cerebras requires your own account. Connect your Cerebras API key on the [Integrations](/providers/integrations) page before configuring an assistant.
 
 ## Language model
 
-Set `model.provider` to `cerebras` and `model.model` to a supported model.
+Set `model.provider` to `cerebras`. Set `model.model` to the exact model ID of a Cerebras model that your connected account can access.
 
 ```bash
 curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
   -H "Authorization: Bearer $VAPI_API_KEY" \
   -H "Content-Type: application/json" \
   -d '{
-    "model": { "provider": "cerebras", "model": "llama3.1-8b" }
+    "model": {
+      "provider": "cerebras",
+      "model": "YOUR_CEREBRAS_MODEL_ID"
+    }
   }'
 ```
 
 For additional API configuration options, review the [`CerebrasModel` fields](/api-reference/assistants/create#request.body.model.CerebrasModel) in the Create Assistant API reference.
 
-| Model | Model ID |
-| --- | --- |
-| Llama 3.1 8B | `llama3.1-8b` |
-
 ## Related
 
 <CardGroup cols={2}>

diff --git a/fern/providers/model/groq.mdx b/fern/providers/model/groq.mdx
@@ -30,10 +30,6 @@ These are the Groq models currently selectable in Vapi.
 | --- | --- |
 | GPT-OSS 20B | `openai/gpt-oss-20b` |
 | GPT-OSS 120B | `openai/gpt-oss-120b` |
-| Kimi K2 Instruct 0905 | `moonshotai/kimi-k2-instruct-0905` |
-| Llama 4 Scout 17B 16e Instruct | `meta-llama/llama-4-scout-17b-16e-instruct` |
-| Compound Beta | `compound-beta` |
-| Compound Beta Mini | `compound-beta-mini` |
 
 ## Related
 

diff --git a/fern/providers/model/openai.mdx b/fern/providers/model/openai.mdx
@@ -48,6 +48,7 @@ For additional API configuration options, review the [`OpenAIModel` fields](/api
 | GPT 5 Nano | `gpt-5-nano` |
 | GPT 4.1 | `gpt-4.1` |
 | GPT 4.1 Mini | `gpt-4.1-mini` |
+| GPT 4o | `gpt-4o` |
 | GPT 4o Mini | `gpt-4o-mini` |
 | GPT Realtime Cluster | `gpt-realtime-2025-08-28` |
 | GPT Realtime Mini | `gpt-realtime-mini-2025-12-15` |

diff --git a/fern/providers/transcriber/google.mdx b/fern/providers/transcriber/google.mdx
@@ -24,17 +24,15 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
   -H "Authorization: Bearer $VAPI_API_KEY" \
   -H "Content-Type: application/json" \
   -d '{
-    "transcriber": { "provider": "google", "model": "gemini-2.0-flash" }
+    "transcriber": { "provider": "google", "model": "gemini-2.5-flash" }
   }'
 ```
 
 For additional API configuration options, review the [`GoogleTranscriber` fields](/api-reference/assistants/create#request.body.transcriber.GoogleTranscriber) in the Create Assistant API reference.
 
 | Model | Model ID |
 | --- | --- |
-| Gemini 2.0 Flash | `gemini-2.0-flash` |
-| Gemini 2.0 Flash Lite | `gemini-2.0-flash-lite` |
-| Gemini 1.5 Pro | `gemini-1.5-pro` |
+| Gemini 2.5 Flash | `gemini-2.5-flash` |
 
 Vapi defaults Google transcription to English. Set `transcriber.language` to `Multilingual` to use multilingual transcription; the value is case-sensitive. Google's [available languages](https://ai.google.dev/gemini-api/docs/models/gemini#available-languages) describe provider-level coverage, while the table below contains the language values accepted by Vapi.
 

diff --git a/fern/providers/transcriber/overview.mdx b/fern/providers/transcriber/overview.mdx
@@ -27,7 +27,6 @@ The provider string is the exact value you pass in `transcriber.provider`.
 | [OpenAI](/providers/transcriber/openai#speech-to-text) | `openai` |
 | [Soniox](/providers/transcriber/soniox#speech-to-text) | `soniox` |
 | [Speechmatics](/providers/transcriber/speechmatics#speech-to-text) | `speechmatics` |
-| [Talkscriber](/providers/transcriber/talkscriber#speech-to-text) | `talkscriber` |
 | [xAI](/providers/transcriber/xai#speech-to-text) | `xai` |
 
 ## Related

diff --git a/fern/providers/transcriber/soniox.mdx b/fern/providers/transcriber/soniox.mdx
@@ -34,7 +34,6 @@ For additional API configuration options, review the [`SonioxTranscriber` fields
 
 | Model | Model ID |
 | --- | --- |
-| Soniox STT Real-Time v4 | `stt-rt-v4` |
 | Soniox STT Real-Time v5 | `stt-rt-v5` |
 
 ### Automatic language detection