diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 1f2bd7d7837..446af103664 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -22775,6 +22775,32 @@
         "output_cost_per_token_batches": 1e-06,
         "source": "https://developers.openai.com/api/docs/pricing"
     },
+    "deepgram/aura": {
+        "input_cost_per_character": 1.5e-05,
+        "litellm_provider": "deepgram",
+        "metadata": {
+            "calculation": "$0.0150/1000 characters = $0.000015 per character",
+            "note": "Aura-1 text-to-speech voices (aura-<voice>-<lang>), pay as you go"
+        },
+        "mode": "audio_speech",
+        "source": "https://deepgram.com/pricing",
+        "supported_endpoints": [
+            "/v1/speak"
+        ]
+    },
+    "deepgram/aura-2": {
+        "input_cost_per_character": 3e-05,
+        "litellm_provider": "deepgram",
+        "metadata": {
+            "calculation": "$0.030/1000 characters = $0.00003 per character",
+            "note": "Aura-2 text-to-speech voices (aura-2-<voice>-<lang>), pay as you go"
+        },
+        "mode": "audio_speech",
+        "source": "https://deepgram.com/pricing",
+        "supported_endpoints": [
+            "/v1/speak"
+        ]
+    },
     "deepgram/base": {
         "input_cost_per_second": 0.00020833,
         "litellm_provider": "deepgram",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 1f2bd7d7837..446af103664 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -22775,6 +22775,32 @@
         "output_cost_per_token_batches": 1e-06,
         "source": "https://developers.openai.com/api/docs/pricing"
     },
+    "deepgram/aura": {
+        "input_cost_per_character": 1.5e-05,
+        "litellm_provider": "deepgram",
+        "metadata": {
+            "calculation": "$0.0150/1000 characters = $0.000015 per character",
+            "note": "Aura-1 text-to-speech voices (aura-<voice>-<lang>), pay as you go"
+        },
+        "mode": "audio_speech",
+        "source": "https://deepgram.com/pricing",
+        "supported_endpoints": [
+            "/v1/speak"
+        ]
+    },
+    "deepgram/aura-2": {
+        "input_cost_per_character": 3e-05,
+        "litellm_provider": "deepgram",
+        "metadata": {
+            "calculation": "$0.030/1000 characters = $0.00003 per character",
+            "note": "Aura-2 text-to-speech voices (aura-2-<voice>-<lang>), pay as you go"
+        },
+        "mode": "audio_speech",
+        "source": "https://deepgram.com/pricing",
+        "supported_endpoints": [
+            "/v1/speak"
+        ]
+    },
     "deepgram/base": {
         "input_cost_per_second": 0.00020833,
         "litellm_provider": "deepgram",
diff --git a/tests/unit/llms/deepgram/test_deepgram_common_utils.py b/tests/unit/llms/deepgram/test_deepgram_common_utils.py
index 530888b70c4..7f480d3459f 100644
--- a/tests/unit/llms/deepgram/test_deepgram_common_utils.py
+++ b/tests/unit/llms/deepgram/test_deepgram_common_utils.py
@@ -324,3 +324,23 @@ def test_deepgram_listen_is_priced(
 )
 def test_deepgram_listen_addon_pricing_models(upstream_url: str, expected: tuple[str, ...]):
     assert deepgram_listen_addon_pricing_models(upstream_url) == expected
+
+
+@pytest.mark.usefixtures("local_model_cost_map")
+@pytest.mark.parametrize(
+    ("pricing_model", "usd_per_thousand_characters"),
+    [
+        pytest.param("aura-2", 0.030, id="aura-2"),
+        pytest.param("aura", 0.015, id="aura-1"),
+    ],
+)
+def test_aura_rows_bill_speech_per_character_at_the_published_rate(
+    pricing_model: str, usd_per_thousand_characters: float
+):
+    """Pay as you go rates from https://deepgram.com/pricing, checked 2026-10-26"""
+    prompt_cost, completion_cost = litellm.cost_per_token(
+        model=pricing_model, custom_llm_provider="deepgram", call_type="speech", prompt_characters=1000
+    )
+
+    assert prompt_cost == pytest.approx(usd_per_thousand_characters)
+    assert completion_cost == 0.0
diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py
index 146e2df6413..07747ac5702 100644
--- a/tests/unit/test_utils.py
+++ b/tests/unit/test_utils.py
@@ -1252,6 +1252,7 @@ _COST_MAP_ROW_SCHEMA: Final = {
                         "/v1/videos",
                         "/vertex_ai/live",
                         "/v1/listen",
+                        "/v1/speak",
                         "/v1/systemone",
                         "/v1/decisions",
                         "/v1beta/interactions",