Skip to content

Commit 1fa3f7e

Browse files
goergenjgoergenj
committed
Remove gpt-40-realtime-preview model and update api-version excpept in sdk code samples
1 parent cbdc84b commit 1fa3f7e

File tree

7 files changed

+37
-38
lines changed

7 files changed

+37
-38
lines changed

‎articles/ai-services/speech-service/includes/quickstarts/voice-live-agents/python.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,10 @@
11
---
22
manager: nitinme
3-
author: PatrickFarley
4-
ms.author: pafarley
3+
author: goergenj
4+
ms.author: jagoerge
55
ms.service: azure-ai-openai
66
ms.topic: include
7-
ms.date: 7/31/2025
7+
ms.date: 9/26/2025
88
---
99

1010
In this article, you learn how to use Azure AI Speech voice live with [Azure AI Foundry Agent Service](/azure/ai-foundry/agents/overview) using Python code.
@@ -165,7 +165,7 @@ client = AsyncAzureVoiceLive(
165165
endpoint = os.environ.get("AZURE_VOICE_LIVE_ENDPOINT") or "<https://your-endpoint.azure.com/>"
166166
agent_id = os.environ.get("AI_FOUNDRY_AGENT_ID") or "<your-agent-id>"
167167
project_name = os.environ.get("AI_FOUNDRY_PROJECT_NAME") or "<your-project-name>"
168-
api_version = os.environ.get("AZURE_VOICE_LIVE_API_VERSION") or "2025-05-01-preview"
168+
api_version = os.environ.get("AZURE_VOICE_LIVE_API_VERSION") or "2025-10-01"
169169
api_key = os.environ.get("AZURE_VOICE_LIVE_API_KEY") or "<your-api-key>"
170170
171171
# For the recommended keyless authentication, get and
@@ -669,7 +669,7 @@ The `voicelive.log` file contains information about the connection to the Voice
669669
670670
```text
671671
2025-07-29 09:43:32,574:websockets.client:DEBUG:= connection is CONNECTING
672-
2025-07-29 09:43:32,825:websockets.client:DEBUG:> GET /voice-live/realtime?api-version=2025-05-01-preview&agent-project-name=contoso-proj-agentic&agent-id=<your-agent-id>&agent-access-token=<your-token>&debug=on HTTP/1.1
672+
2025-07-29 09:43:32,825:websockets.client:DEBUG:> GET /voice-live/realtime?api-version=2025-10-01&agent-project-name=contoso-proj-agentic&agent-id=<your-agent-id>&agent-access-token=<your-token>&debug=on HTTP/1.1
673673
2025-07-29 09:43:32,825:websockets.client:DEBUG:> Host: your-ai-foundry-resource.cognitiveservices.azure.com
674674
2025-07-29 09:43:32,825:websockets.client:DEBUG:> Upgrade: websocket
675675
2025-07-29 09:43:32,825:websockets.client:DEBUG:> Connection: Upgrade
@@ -864,7 +864,7 @@ def main() -> None:
864864
endpoint = os.environ.get("AZURE_VOICE_LIVE_ENDPOINT") or "<https://your-endpoint.azure.com/>"
865865
agent_id = os.environ.get("AI_FOUNDRY_AGENT_ID") or "<your-agent-id>"
866866
agent_connection_string = os.environ.get("AI_FOUNDRY_AGENT_CONNECTION_STRING") or "<your-agent-connection-string>"
867-
api_version = os.environ.get("AZURE_VOICE_LIVE_API_VERSION") or "2025-05-01-preview"
867+
api_version = os.environ.get("AZURE_VOICE_LIVE_API_VERSION") or "2025-10-01"
868868
api_key = os.environ.get("AZURE_VOICE_LIVE_API_KEY") or "<your-api-key>"
869869
870870
# For the recommended keyless authentication, get and

‎articles/ai-services/speech-service/includes/quickstarts/voice-live-agents/resource-authentication.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
11
---
2-
author: PatrickFarley
3-
ms.author: pafarley
2+
author: goergenj
3+
ms.author: jagoerge
44
ms.service: azure-ai-speech
55
ms.topic: include
6-
ms.date: 7/31/2025
6+
ms.date: 9/26/2025
77
---
88

99
Create a new file named `.env` in the folder where you want to run the code.
@@ -14,7 +14,7 @@ In the `.env` file, add the following environment variables for authentication:
1414
AZURE_VOICE_LIVE_ENDPOINT=<your_endpoint>
1515
AI_FOUNDRY_PROJECT_NAME=<your_project_name>
1616
AI_FOUNDRY_AGENT_ID=<your_agent_id>
17-
AZURE_VOICE_LIVE_API_VERSION=2025-05-01-preview
17+
AZURE_VOICE_LIVE_API_VERSION=2025-10-01
1818
AZURE_VOICE_LIVE_API_KEY=<your_api_key> # Only required if using API key authentication
1919
```
2020

@@ -27,7 +27,7 @@ Replace the default values with your actual project name, agent ID, API version,
2727
| `AZURE_VOICE_LIVE_ENDPOINT` | This value can be found in the **Keys and Endpoint** section when examining your resource from the Azure portal. |
2828
| `AI_FOUNDRY_PROJECT_NAME` | The name of your Azure AI Foundry project. |
2929
| `AI_FOUNDRY_AGENT_ID` | The ID of your Azure AI Foundry agent. |
30-
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-05-01-preview`. |
30+
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-10-01`. |
3131

3232
Learn more about [keyless authentication](/azure/ai-services/authentication) and [setting environment variables](/azure/ai-services/cognitive-services-environment-variables).
3333

@@ -38,7 +38,7 @@ Learn more about [keyless authentication](/azure/ai-services/authentication) and
3838
| `AZURE_VOICE_LIVE_ENDPOINT` | This value can be found in the **Keys and Endpoint** section when examining your resource from the Azure portal. |
3939
| `AI_FOUNDRY_PROJECT_NAME` | The name of your Azure AI Foundry project. |
4040
| `AI_FOUNDRY_AGENT_ID` | The ID of your Azure AI Foundry agent. |
41-
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-05-01-preview`. |
41+
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-10-01`. |
4242
| `AZURE_VOICE_LIVE_API_KEY` | This value can be found in the **Keys and Endpoint** section when examining your resource from the Azure portal. You can use either `KEY1` or `KEY2`.|
4343

4444
Learn more about [finding API keys](/azure/ai-services/cognitive-services-environment-variables) and [setting environment variables](/azure/ai-services/cognitive-services-environment-variables).

‎articles/ai-services/speech-service/includes/quickstarts/voice-live-api/resource-authentication.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,9 @@
11
---
2-
author: PatrickFarley
3-
ms.author: pafarley
2+
author: goergenj
3+
ms.author: jagoerge
44
ms.service: azure-ai-speech
55
ms.topic: include
6-
ms.date: 7/31/2025
6+
ms.date: 9/26/2025
77
---
88

99
Create a new file named `.env` in the folder where you want to run the code.
@@ -13,7 +13,7 @@ In the `.env` file, add the following environment variables for authentication:
1313
```plaintext
1414
AZURE_VOICE_LIVE_ENDPOINT=<your_endpoint>
1515
VOICE_LIVE_MODEL=<your_model>
16-
AZURE_VOICE_LIVE_API_VERSION=2025-05-01-preview
16+
AZURE_VOICE_LIVE_API_VERSION=2025-10-01
1717
AZURE_VOICE_LIVE_API_KEY=<your_api_key> # Only required if using API key authentication
1818
```
1919

@@ -25,7 +25,7 @@ Replace the default values with your actual endpoint, model, API version, and AP
2525
|--------------------------|-------------|
2626
| `AZURE_VOICE_LIVE_ENDPOINT` | This value can be found in the **Keys and Endpoint** section when examining your resource from the Azure portal. |
2727
| `AZURE_VOICE_LIVE_MODEL` | The model you want to use. For example, `gpt-4o` or `gpt-4o-mini-realtime-preview`. For more information about models availability, see the [Voice Live API overview documentation](../../../voice-live.md). |
28-
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-05-01-preview`. |
28+
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-10-01`. |
2929

3030
Learn more about [keyless authentication](/azure/ai-services/authentication) and [setting environment variables](/azure/ai-services/cognitive-services-environment-variables).
3131

@@ -35,7 +35,7 @@ Learn more about [keyless authentication](/azure/ai-services/authentication) and
3535
|--------------------------|-------------|
3636
| `AZURE_VOICE_LIVE_ENDPOINT` | This value can be found in the **Keys and Endpoint** section when examining your resource from the Azure portal. |
3737
| `AZURE_VOICE_LIVE_MODEL` | The model you want to use. For example, `gpt-4o` or `gpt-4o-mini-realtime-preview`. For more information about models availability, see the [Voice Live API overview documentation](../../../voice-live.md). |
38-
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-05-01-preview`. |
38+
| `AZURE_VOICE_LIVE_API_VERSION`| The API version you want to use. For example, `2025-10-01`. |
3939
| `AZURE_VOICE_LIVE_API_KEY` | This value can be found in the **Keys and Endpoint** section when examining your resource from the Azure portal. You can use either `KEY1` or `KEY2`.|
4040

4141
Learn more about [finding API keys](/azure/ai-services/cognitive-services-environment-variables) and [setting environment variables](/azure/ai-services/cognitive-services-environment-variables).

‎articles/ai-services/speech-service/regions.md‎

Lines changed: 12 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -174,18 +174,18 @@ The regions in these tables support most of the core features of the Speech serv
174174

175175
# [Voice live](#tab/voice-live)
176176

177-
| **Region** | **gpt-realtime** | **gpt-4o-realtime-preview** (Preview) | **gpt-4o-mini-realtime-preview** (Preview) | **gpt-4o** | **gpt-4o-mini** | **gpt-4.1** | **gpt-4.1-mini** | **gpt-5** (Preview) | **gpt-5-mini** (Preview) | **gpt-5-nano** (Preview) | **gpt-5-chat** (Preview) | **phi4-mm-realtime** (Preview) | **phi4-mini** (Preview) |
178-
|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|
179-
| centralindia | Cross-region<sup>1</sup> | Cross-region<sup>1</sup> | Cross-region<sup>1</sup> | Global standard | Global standard | Global standard | Global standard | - | - | - | - | - | - |
180-
| eastus2 | Global standard | Global standard | Global standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Global standard | Regional | Regional |
181-
| southeastasia | - | - | - | - | - | Global standard | Global standard | - | - | - | - | Regional | Regional |
182-
| swedencentral | Global standard | Global standard | Global standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Global standard | Regional | Regional |
183-
| westus2 | Cross-region<sup>2</sup> | Cross-region<sup>2</sup> | Cross-region<sup>2</sup> | Data zone standard | Data zone standard | Data zone standard | Data zone standard | - | - | - | - | Regional | Regional |
184-
|australiaeast| - | - | - | Global standard | Global standard | Global standard | Global standard | - | - | - | - | - | - |
185-
|japaneast| - | - | - | Global standard | Global standard | Global standard | Global standard | - | - | - | - | Regional | Regional |
186-
|eastus| - | - | - | Data zone standard | Data zone standard | Data zone standard | Data zone standard | - | - | - | - | - | - |
187-
|uksouth| - | - | - | Global standard | Global standard | Global standard | Global standard | - | - | - | - | - | - |
188-
|westeurope| - | - | - | Data zone standard | Data zone standard | Data zone standard | Data zone standard | - | - | - | - | - | - |
177+
| **Region** | **gpt-realtime** | **gpt-4o-mini-realtime-preview** (Preview) | **gpt-4o** | **gpt-4o-mini** | **gpt-4.1** | **gpt-4.1-mini** | **gpt-5** (Preview) | **gpt-5-mini** (Preview) | **gpt-5-nano** (Preview) | **gpt-5-chat** (Preview) | **phi4-mm-realtime** (Preview) | **phi4-mini** (Preview) |
178+
|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|-----|
179+
| centralindia | Cross-region<sup>1</sup> | Cross-region<sup>1</sup> | Global standard | Global standard | Global standard | Global standard | - | - | - | - | - | - |
180+
| eastus2 | Global standard | Global standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Global standard | Regional | Regional |
181+
| southeastasia | - | - | - | - | Global standard | Global standard | - | - | - | - | Regional | Regional |
182+
| swedencentral | Global standard | Global standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Data zone standard | Global standard | Regional | Regional |
183+
| westus2 | Cross-region<sup>2</sup> | Cross-region<sup>2</sup> | Data zone standard | Data zone standard | Data zone standard | Data zone standard | - | - | - | - | Regional | Regional |
184+
|australiaeast| - | - | Global standard | Global standard | Global standard | Global standard | - | - | - | - | - | - |
185+
|japaneast| - | - | Global standard | Global standard | Global standard | Global standard | - | - | - | - | Regional | Regional |
186+
|eastus| - | - | Data zone standard | Data zone standard | Data zone standard | Data zone standard | - | - | - | - | - | - |
187+
|uksouth| - | - | Global standard | Global standard | Global standard | Global standard | - | - | - | - | - | - |
188+
|westeurope| - | - | Data zone standard | Data zone standard | Data zone standard | Data zone standard | - | - | - | - | - | - |
189189

190190
<sup>1</sup> The Azure AI Foundry resource must be in Central India. Azure AI Speech features remain in Central India. The voice live API uses Sweden Central as needed for generative AI load balancing.
191191

‎articles/ai-services/speech-service/voice-live-how-to.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -30,10 +30,10 @@ An [Azure AI Foundry resource](../multi-service-resource.md) is required to acce
3030

3131
### WebSocket endpoint
3232

33-
The WebSocket endpoint for the voice live API is `wss://<your-ai-foundry-resource-name>.services.ai.azure.com/voice-live/realtime?api-version=2025-05-01-preview` or, for older resources, `wss://<your-ai-foundry-resource-name>.cognitiveservices.azure.com/voice-live/realtime?api-version=2025-05-01-preview`.
33+
The WebSocket endpoint for the voice live API is `wss://<your-ai-foundry-resource-name>.services.ai.azure.com/voice-live/realtime?api-version=2025-10-01` or, for older resources, `wss://<your-ai-foundry-resource-name>.cognitiveservices.azure.com/voice-live/realtime?api-version=2025-10-01`.
3434
The endpoint is the same for all models. The only difference is the required `model` query parameter, or, when using the Agent service, the `agent_id` and `project_id` parameters.
3535

36-
For example, an endpoint for a resource with a custom domain would be `wss://<your-ai-foundry-resource-name>.services.ai.azure.com/voice-live/realtime?api-version=2025-05-01-preview&model=gpt-realtime`
36+
For example, an endpoint for a resource with a custom domain would be `wss://<your-ai-foundry-resource-name>.services.ai.azure.com/voice-live/realtime?api-version=2025-10-01&model=gpt-realtime`
3737

3838
### Credentials
3939

‎articles/ai-services/speech-service/voice-live-language-support.md‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ The voice live API supports multiple languages and configuration options. In thi
2222

2323
## [Speech input](#tab/speechinput)
2424

25-
Depending on which model is being used voice live speech input is processed either by one of the multimodal models (for example, `gpt-realtime`, `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, and `phi4-mm-realtime`) or by `azure speech to text` models.
25+
Depending on which model is being used voice live speech input is processed either by one of the multimodal models (for example, `gpt-realtime`, `gpt-4o-mini-realtime-preview`, and `phi4-mm-realtime`) or by `azure speech to text` models.
2626

2727
### Azure speech to text supported languages
2828

@@ -78,11 +78,11 @@ To configure a single or multiple languages not supported by the multimodal mode
7878
}
7979
```
8080

81-
### gpt-realtime, gpt-4o-realtime-preview and gpt-4o-mini-realtime-preview supported languages
81+
### gpt-realtime and gpt-4o-mini-realtime-preview supported languages
8282

8383
While the underlying model was trained on 98 languages, OpenAI only lists the languages that exceeded <50% word error rate (WER) which is an industry standard benchmark for speech to text model accuracy. The model returns results for languages not listed but the quality will be low.
8484

85-
The following languages are supported by `gpt-realtime`, `gpt-4o-realtime-preview` and `gpt-4o-mini-realtime-preview`:
85+
The following languages are supported by `gpt-realtime` and `gpt-4o-mini-realtime-preview`:
8686
- Afrikaans
8787
- Arabic
8888
- Armenian
@@ -175,7 +175,7 @@ Multimodal models don't require a language configuration for the general process
175175

176176
## [Speech output](#tab/speechoutput)
177177

178-
Depending on which model is being used voice live speech output is processed either by one of the multimodal OpenAI voices integrated into `gpt-realtime`, `gpt-4o-realtime-preview`, and `gpt-4o-mini-realtime-preview` or by `azure text to speech` voices.
178+
Depending on which model is being used voice live speech output is processed either by one of the multimodal OpenAI voices integrated into `gpt-realtime` and `gpt-4o-mini-realtime-preview` or by `azure text to speech` voices.
179179

180180
### Azure text to speech supported languages
181181

‎articles/ai-services/speech-service/voice-live.md‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -74,7 +74,6 @@ The voice live API supports the following models. For supported regions, see the
7474
| Model | Description |
7575
| ------------------------------ | ----------- |
7676
| `gpt-realtime` | GPT real-time + option to use Azure text to speech voices including custom voice for audio. |
77-
| `gpt-4o-realtime-preview` | GPT-4o real-time preview + option to use Azure text to speech voices including custom voice for audio. |
7877
| `gpt-4o-mini-realtime-preview` | GPT-4o mini real-time preview + option to use Azure text to speech voices including custom voice for audio. |
7978
| `gpt-4o` | GPT-4o + audio input through Azure speech to text + audio output through Azure text to speech voices including custom voice. |
8079
| `gpt-4o-mini` | GPT-4o mini + audio input through Azure speech to text + audio output through Azure text to speech voices including custom voice. |
@@ -113,7 +112,7 @@ You don't select a tier. You choose a generative AI model and the corresponding
113112

114113
| Pricing category | Models |
115114
| ----- | ------ |
116-
| Voice live pro | `gpt-realtime`, `gpt-4o-realtime`, `gpt-4o`, `gpt-4.1`, `gpt-5`, `gpt-5-chat` |
115+
| Voice live pro | `gpt-realtime`, `gpt-4o`, `gpt-4.1`, `gpt-5`, `gpt-5-chat` |
117116
| Voice live basic | `gpt-4o-mini-realtime-preview`, `gpt-4o-mini`, `gpt-4.1-mini`, `gpt-5-mini` |
118117
| Voice live lite | `gpt-5-nano`,`phi4-mm-realtime`, `phi4-mini` |
119118

0 commit comments

Comments
 (0)