diff --git a/src/assets/images/workers-ai/ibm.svg b/src/assets/images/workers-ai/ibm.svg
new file mode 100644
index 00000000000000..b126ca77f6fc21
--- /dev/null
+++ b/src/assets/images/workers-ai/ibm.svg
@@ -0,0 +1,2 @@
+
+
\ No newline at end of file
diff --git a/src/components/models/data.ts b/src/components/models/data.ts
index 6ea493e7532f15..f02fa88fa503fa 100644
--- a/src/components/models/data.ts
+++ b/src/components/models/data.ts
@@ -10,6 +10,7 @@ import qwen from "../../assets/images/workers-ai/qwen.svg";
import blackforestlabs from "../../assets/images/workers-ai/blackforestlabs.svg";
import deepgram from "../../assets/images/workers-ai/deepgram.svg";
import leonardo from "../../assets/images/workers-ai/leonardo.svg";
+import ibm from "../../assets/images/workers-ai/ibm.svg";
export const authorData: Record = {
openai: {
@@ -64,4 +65,8 @@ export const authorData: Record = {
name: "Leonardo",
logo: leonardo.src,
},
+ "ibm-granite": {
+ name: "IBM",
+ logo: ibm.src,
+ },
};
diff --git a/src/content/docs/workers-ai/platform/pricing.mdx b/src/content/docs/workers-ai/platform/pricing.mdx
index 13c1d2fc4d3604..a86ea5063d8990 100644
--- a/src/content/docs/workers-ai/platform/pricing.mdx
+++ b/src/content/docs/workers-ai/platform/pricing.mdx
@@ -88,6 +88,8 @@ The Price in Tokens column is equivalent to the Price in Neurons column - the di
| @cf/deepgram/nova-3 | $0.0052 per audio minute input
| 472.73 neurons per audio minute input
|
| @cf/deepgram/nova-3 (WebSocket)| $0.0092 per audio minute input
| 836.36 neurons per audio minute input
|
| @cf/pipecat-ai/smart-turn-v2 | $0.00033795 per audio minute input
| 0.51 neurons per audio minute input
|
+| @cf/deepgram/aura-2-en | $0.030 per 1k characters input
| 2.73 neurons per 1k characters input
|
+| @cf/deepgram/aura-2-es | $0.030 per 1k characters input
| 2.73 neurons per 1k characters input
|
## Other model pricing
diff --git a/src/content/release-notes/workers-ai.yaml b/src/content/release-notes/workers-ai.yaml
index 6b9e42b3c1345c..132d7d99ae2871 100644
--- a/src/content/release-notes/workers-ai.yaml
+++ b/src/content/release-notes/workers-ai.yaml
@@ -3,6 +3,11 @@ link: "/workers-ai/changelog/"
productName: Workers AI
productLink: "/workers-ai/"
entries:
+ - publish_date: "2025-10-21"
+ title: New voice and LLM models on Workers AI
+ description: |-
+ - Deepgram Aura 2 brings new text-to-speech capabilities to Workers AI. Check out [`@cf/deepgram/aura-2-en`](/workers-ai/models/aura-2-en/) and [`@cf/deepgram/aura-2-es`](/workers-ai/models/aura-2-es/) on how to use the new models.
+ - IBM Granite model is also up! This new LLM model is small but mighty, take a look at the docs for more [`@cf/ibm-granite/granite-4.0-h-micro`](/workers-ai/models/granite-4.0-h-micro/)
- publish_date: "2025-10-02"
title: Deepgram Flux now available on Workers AI
description: |-
diff --git a/src/content/workers-ai-models/aura-2-en.json b/src/content/workers-ai-models/aura-2-en.json
new file mode 100644
index 00000000000000..8462f247fc8df6
--- /dev/null
+++ b/src/content/workers-ai-models/aura-2-en.json
@@ -0,0 +1,134 @@
+{
+ "id": "01564c52-8717-47dc-8efd-907a2ca18301",
+ "source": 1,
+ "name": "@cf/deepgram/aura-2-en",
+ "description": "Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.",
+ "task": {
+ "id": "b52660a1-9a95-4ab2-8b1d-f232be34604a",
+ "name": "Text-to-Speech",
+ "description": "Text-to-Speech (TTS) is the task of generating natural sounding speech given text input. TTS models can be extended to have a single model that generates speech for multiple speakers and multiple languages."
+ },
+ "created_at": "2025-10-09 22:19:34.483",
+ "tags": [],
+ "properties": [
+ {
+ "property_id": "async_queue",
+ "value": "true"
+ },
+ {
+ "property_id": "price",
+ "value": [
+ {
+ "unit": "per 1k chars input",
+ "price": 0.03,
+ "currency": "USD"
+ }
+ ]
+ },
+ {
+ "property_id": "partner",
+ "value": "true"
+ },
+ {
+ "property_id": "realtime",
+ "value": "true"
+ }
+ ],
+ "schema": {
+ "input": {
+ "type": "object",
+ "properties": {
+ "speaker": {
+ "type": "string",
+ "enum": [
+ "amalthea",
+ "andromeda",
+ "apollo",
+ "arcas",
+ "aries",
+ "asteria",
+ "athena",
+ "atlas",
+ "aurora",
+ "callista",
+ "cora",
+ "cordelia",
+ "delia",
+ "draco",
+ "electra",
+ "harmonia",
+ "helena",
+ "hera",
+ "hermes",
+ "hyperion",
+ "iris",
+ "janus",
+ "juno",
+ "jupiter",
+ "luna",
+ "mars",
+ "minerva",
+ "neptune",
+ "odysseus",
+ "ophelia",
+ "orion",
+ "orpheus",
+ "pandora",
+ "phoebe",
+ "pluto",
+ "saturn",
+ "thalia",
+ "theia",
+ "vesta",
+ "zeus"
+ ],
+ "default": "luna",
+ "description": "Speaker used to produce the audio."
+ },
+ "encoding": {
+ "type": "string",
+ "enum": [
+ "linear16",
+ "flac",
+ "mulaw",
+ "alaw",
+ "mp3",
+ "opus",
+ "aac"
+ ],
+ "description": "Encoding of the output audio."
+ },
+ "container": {
+ "type": "string",
+ "enum": [
+ "none",
+ "wav",
+ "ogg"
+ ],
+ "description": "Container specifies the file format wrapper for the output audio. The available options depend on the encoding type.."
+ },
+ "text": {
+ "type": "string",
+ "description": "The text content to be converted to speech"
+ },
+ "sample_rate": {
+ "type": "number",
+ "description": "Sample Rate specifies the sample rate for the output audio. Based on the encoding, different sample rates are supported. For some encodings, the sample rate is not configurable"
+ },
+ "bit_rate": {
+ "type": "number",
+ "description": "The bitrate of the audio in bits per second. Choose from predefined ranges or specific values based on the encoding type."
+ }
+ },
+ "required": [
+ "text"
+ ]
+ },
+ "output": {
+ "type": "string",
+ "contentType": "audio/mpeg",
+ "format": "binary",
+ "description": "The generated audio in MP3 format"
+ }
+ }
+}
\ No newline at end of file
diff --git a/src/content/workers-ai-models/aura-2-es.json b/src/content/workers-ai-models/aura-2-es.json
new file mode 100644
index 00000000000000..186f29f85bbf9b
--- /dev/null
+++ b/src/content/workers-ai-models/aura-2-es.json
@@ -0,0 +1,104 @@
+{
+ "id": "c5255b94-2161-4779-bd25-54f061829a2a",
+ "source": 1,
+ "name": "@cf/deepgram/aura-2-es",
+ "description": "Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.",
+ "task": {
+ "id": "b52660a1-9a95-4ab2-8b1d-f232be34604a",
+ "name": "Text-to-Speech",
+ "description": "Text-to-Speech (TTS) is the task of generating natural sounding speech given text input. TTS models can be extended to have a single model that generates speech for multiple speakers and multiple languages."
+ },
+ "created_at": "2025-10-09 22:42:37.002",
+ "tags": [],
+ "properties": [
+ {
+ "property_id": "async_queue",
+ "value": "true"
+ },
+ {
+ "property_id": "price",
+ "value": [
+ {
+ "unit": "per 1k chars input",
+ "price": 0.03,
+ "currency": "USD"
+ }
+ ]
+ },
+ {
+ "property_id": "partner",
+ "value": "true"
+ },
+ {
+ "property_id": "realtime",
+ "value": "true"
+ }
+ ],
+ "schema": {
+ "input": {
+ "type": "object",
+ "properties": {
+ "speaker": {
+ "type": "string",
+ "enum": [
+ "sirio",
+ "nestor",
+ "carina",
+ "celeste",
+ "alvaro",
+ "diana",
+ "aquila",
+ "selena",
+ "estrella",
+ "javier"
+ ],
+ "default": "aquila",
+ "description": "Speaker used to produce the audio."
+ },
+ "encoding": {
+ "type": "string",
+ "enum": [
+ "linear16",
+ "flac",
+ "mulaw",
+ "alaw",
+ "mp3",
+ "opus",
+ "aac"
+ ],
+ "description": "Encoding of the output audio."
+ },
+ "container": {
+ "type": "string",
+ "enum": [
+ "none",
+ "wav",
+ "ogg"
+ ],
+ "description": "Container specifies the file format wrapper for the output audio. The available options depend on the encoding type.."
+ },
+ "text": {
+ "type": "string",
+ "description": "The text content to be converted to speech"
+ },
+ "sample_rate": {
+ "type": "number",
+ "description": "Sample Rate specifies the sample rate for the output audio. Based on the encoding, different sample rates are supported. For some encodings, the sample rate is not configurable"
+ },
+ "bit_rate": {
+ "type": "number",
+ "description": "The bitrate of the audio in bits per second. Choose from predefined ranges or specific values based on the encoding type."
+ }
+ },
+ "required": [
+ "text"
+ ]
+ },
+ "output": {
+ "type": "string",
+ "contentType": "audio/mpeg",
+ "format": "binary",
+ "description": "The generated audio in MP3 format"
+ }
+ }
+}
\ No newline at end of file