SDK regeneration

.fern/metadata.json

@@ -1,5 +1,5 @@
 {
-  "cliVersion": "4.62.5",
+  "cliVersion": "4.65.2",
   "generatorName": "fernapi/fern-python-sdk",
   "generatorVersion": "4.61.0",
   "generatorConfig": {
@@ -64,6 +64,6 @@
       }
     ]
   },
-  "originGitCommit": "a07a0deaa640e8b286f9c8e4e47426b37a083a67",
-  "sdkVersion": "0.13.11"
+  "originGitCommit": "274a9e627c776728cbf8da2fc71627448d122f99",
+  "sdkVersion": "0.13.12"
 }

pyproject.toml

@@ -4,7 +4,7 @@ dynamic = ["version"]
 
 [tool.poetry]
 name = "hume"
-version = "0.13.11"
+version = "0.13.12"
 description = "A Python SDK for Hume AI"
 readme = "README.md"
 authors = []

src/hume/core/client_wrapper.py

@@ -28,12 +28,12 @@ def get_headers(self) -> typing.Dict[str, str]:
         import platform
 
         headers: typing.Dict[str, str] = {
-            "User-Agent": "hume/0.13.11",
+            "User-Agent": "hume/0.13.12",
             "X-Fern-Language": "Python",
             "X-Fern-Runtime": f"python/{platform.python_version()}",
             "X-Fern-Platform": f"{platform.system().lower()}/{platform.release()}",
             "X-Fern-SDK-Name": "hume",
-            "X-Fern-SDK-Version": "0.13.11",
+            "X-Fern-SDK-Version": "0.13.12",
             **(self.get_custom_headers() or {}),
         }
         if self.api_key is not None:

src/hume/empathic_voice/tools/client.py

@@ -447,7 +447,7 @@ def delete_tool_version(
             api_key="YOUR_API_KEY",
         )
         client.empathic_voice.tools.delete_tool_version(
-            id="",
+            id="your-tool-id",
             version=1,
         )
         """
@@ -1008,7 +1008,7 @@ async def delete_tool_version(
 
         async def main() -> None:
             await client.empathic_voice.tools.delete_tool_version(
-                id="",
+                id="your-tool-id",
                 version=1,
             )
 

src/hume/tts/stream_input/client.py

@@ -50,6 +50,7 @@ def connect(
         instant_mode: typing.Optional[bool] = None,
         no_binary: typing.Optional[bool] = None,
         strip_headers: typing.Optional[bool] = None,
+        temperature: typing.Optional[float] = None,
         version: typing.Optional[OctaveVersion] = None,
         api_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -84,6 +85,16 @@ def connect(
         strip_headers : typing.Optional[bool]
             If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).
 
+        temperature : typing.Optional[float]
+            Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.
+
+            **This is an experimental parameter.** It is recommended to use the default values for most use cases.
+
+            Defaults when omitted:
+            - Octave 1 voice creation (no voice specified): `0.9`
+            - Octave 1 text-to-speech: `0.8`
+            - Octave 2 text-to-speech: `0.75`
+
         version : typing.Optional[OctaveVersion]
             The version of the Octave Model to use. 1 for the legacy model, 2 for the new model.
 
@@ -111,6 +122,7 @@ def connect(
                         "instant_mode": instant_mode,
                         "no_binary": no_binary,
                         "strip_headers": strip_headers,
+                        "temperature": temperature,
                         "version": version,
                         "api_key": api_key,
                         **(
@@ -171,6 +183,7 @@ async def connect(
         instant_mode: typing.Optional[bool] = None,
         no_binary: typing.Optional[bool] = None,
         strip_headers: typing.Optional[bool] = None,
+        temperature: typing.Optional[float] = None,
         version: typing.Optional[OctaveVersion] = None,
         api_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -205,6 +218,16 @@ async def connect(
         strip_headers : typing.Optional[bool]
             If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).
 
+        temperature : typing.Optional[float]
+            Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.
+
+            **This is an experimental parameter.** It is recommended to use the default values for most use cases.
+
+            Defaults when omitted:
+            - Octave 1 voice creation (no voice specified): `0.9`
+            - Octave 1 text-to-speech: `0.8`
+            - Octave 2 text-to-speech: `0.75`
+
         version : typing.Optional[OctaveVersion]
             The version of the Octave Model to use. 1 for the legacy model, 2 for the new model.
 
@@ -232,6 +255,7 @@ async def connect(
                         "instant_mode": instant_mode,
                         "no_binary": no_binary,
                         "strip_headers": strip_headers,
+                        "temperature": temperature,
                         "version": version,
                         "api_key": api_key,
                         **(

src/hume/tts/stream_input/raw_client.py

@@ -38,6 +38,7 @@ def connect(
         instant_mode: typing.Optional[bool] = None,
         no_binary: typing.Optional[bool] = None,
         strip_headers: typing.Optional[bool] = None,
+        temperature: typing.Optional[float] = None,
         version: typing.Optional[OctaveVersion] = None,
         api_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -72,6 +73,16 @@ def connect(
         strip_headers : typing.Optional[bool]
             If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).
 
+        temperature : typing.Optional[float]
+            Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.
+
+            **This is an experimental parameter.** It is recommended to use the default values for most use cases.
+
+            Defaults when omitted:
+            - Octave 1 voice creation (no voice specified): `0.9`
+            - Octave 1 text-to-speech: `0.8`
+            - Octave 2 text-to-speech: `0.75`
+
         version : typing.Optional[OctaveVersion]
             The version of the Octave Model to use. 1 for the legacy model, 2 for the new model.
 
@@ -99,6 +110,7 @@ def connect(
                         "instant_mode": instant_mode,
                         "no_binary": no_binary,
                         "strip_headers": strip_headers,
+                        "temperature": temperature,
                         "version": version,
                         "api_key": api_key,
                         **(
@@ -148,6 +160,7 @@ async def connect(
         instant_mode: typing.Optional[bool] = None,
         no_binary: typing.Optional[bool] = None,
         strip_headers: typing.Optional[bool] = None,
+        temperature: typing.Optional[float] = None,
         version: typing.Optional[OctaveVersion] = None,
         api_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -182,6 +195,16 @@ async def connect(
         strip_headers : typing.Optional[bool]
             If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).
 
+        temperature : typing.Optional[float]
+            Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.
+
+            **This is an experimental parameter.** It is recommended to use the default values for most use cases.
+
+            Defaults when omitted:
+            - Octave 1 voice creation (no voice specified): `0.9`
+            - Octave 1 text-to-speech: `0.8`
+            - Octave 2 text-to-speech: `0.75`
+
         version : typing.Optional[OctaveVersion]
             The version of the Octave Model to use. 1 for the legacy model, 2 for the new model.
 
@@ -209,6 +232,7 @@ async def connect(
                         "instant_mode": instant_mode,
                         "no_binary": no_binary,
                         "strip_headers": strip_headers,
+                        "temperature": temperature,
                         "version": version,
                         "api_key": api_key,
                         **(

src/hume/tts/types/posted_tts.py

@@ -50,6 +50,18 @@ class PostedTts(UniversalBaseModel):
     If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file. Otherwise, if disabled, each chunk's audio will be its own audio file, each with its own headers (if applicable).
     """
 
+    temperature: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.
+
+    **This is an experimental parameter.** It is recommended to use the default values for most use cases.
+
+    Defaults when omitted:
+    - Octave 1 voice creation (no voice specified): `0.9`
+    - Octave 1 text-to-speech: `0.8`
+    - Octave 2 text-to-speech: `0.75`
+    """
+
     utterances: typing.List[PostedUtterance] = pydantic.Field()
     """
     A list of **Utterances** to be converted to speech output.
@@ -66,7 +78,13 @@ class PostedTts(UniversalBaseModel):
     For a comparison of Octave versions, see the [Octave versions](/docs/text-to-speech-tts/overview#octave-versions) section in the TTS overview.
     """
 
-    instant_mode: typing.Optional[bool] = None
+    instant_mode: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Enables ultra-low latency streaming, significantly reducing the time until the first audio chunk is received. Recommended for real-time applications requiring immediate audio playback. For further details, see our documentation on [instant mode](/docs/text-to-speech-tts/overview#ultra-low-latency-streaming-instant-mode). 
+    - A [voice](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.utterances.voice) must be specified when instant mode is enabled. Dynamic voice generation is not supported with this mode.
+    - Instant mode is only supported for streaming endpoints (e.g., [/v0/tts/stream/json](/reference/text-to-speech-tts/synthesize-json-streaming), [/v0/tts/stream/file](/reference/text-to-speech-tts/synthesize-file-streaming)).
+    - Ensure only a single generation is requested ([num_generations](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.num_generations) must be `1` or omitted).
+    """
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2