sarvamai 0.1.22a4__py3-none-any.whl → 0.1.22a8__py3-none-any.whl

sarvamai/requests/__init__.py

@@ -27,6 +27,16 @@ from .configure_connection_data import ConfigureConnectionDataParams
 from .create_chat_completion_response import CreateChatCompletionResponseParams
 from .diarized_entry import DiarizedEntryParams
 from .diarized_transcript import DiarizedTranscriptParams
+from .doc_digitization_create_job_response import DocDigitizationCreateJobResponseParams
+from .doc_digitization_download_files_response import DocDigitizationDownloadFilesResponseParams
+from .doc_digitization_error_details import DocDigitizationErrorDetailsParams
+from .doc_digitization_error_message import DocDigitizationErrorMessageParams
+from .doc_digitization_job_detail import DocDigitizationJobDetailParams
+from .doc_digitization_job_parameters import DocDigitizationJobParametersParams
+from .doc_digitization_job_status_response import DocDigitizationJobStatusResponseParams
+from .doc_digitization_page_error import DocDigitizationPageErrorParams
+from .doc_digitization_upload_files_response import DocDigitizationUploadFilesResponseParams
+from .doc_digitization_webhook_callback import DocDigitizationWebhookCallbackParams
 from .error_data import ErrorDataParams
 from .error_details import ErrorDetailsParams
 from .error_message import ErrorMessageParams
@@ -89,6 +99,16 @@ __all__ = [
     "CreateChatCompletionResponseParams",
     "DiarizedEntryParams",
     "DiarizedTranscriptParams",
+    "DocDigitizationCreateJobResponseParams",
+    "DocDigitizationDownloadFilesResponseParams",
+    "DocDigitizationErrorDetailsParams",
+    "DocDigitizationErrorMessageParams",
+    "DocDigitizationJobDetailParams",
+    "DocDigitizationJobParametersParams",
+    "DocDigitizationJobStatusResponseParams",
+    "DocDigitizationPageErrorParams",
+    "DocDigitizationUploadFilesResponseParams",
+    "DocDigitizationWebhookCallbackParams",
     "ErrorDataParams",
     "ErrorDetailsParams",
     "ErrorMessageParams",

sarvamai/requests/audio_data.py

@@ -3,7 +3,6 @@
 import typing
 
 import typing_extensions
-from ..types.audio_data_input_audio_codec import AudioDataInputAudioCodec
 
 
 class AudioDataParams(typing_extensions.TypedDict):
@@ -27,8 +26,3 @@ class AudioDataParams(typing_extensions.TypedDict):
     """
     Audio encoding format
     """
-
-    input_audio_codec: typing_extensions.NotRequired[AudioDataInputAudioCodec]
-    """
-    Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
-    """

sarvamai/requests/configure_connection.py

@@ -12,6 +12,10 @@ class ConfigureConnectionParams(typing_extensions.TypedDict):
     This initializes TTS parameters and can be updated at any time during the WebSocket lifecycle
     by sending a new config message. When a config update is sent, any text currently in the buffer
     will be automatically flushed and processed before applying the new configuration.
+
+    **Model-Specific Notes:**
+    - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
+    - **bulbul:v3-beta:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Supports temperature. Default sample rate: 24000 Hz.
     """
 
     type: typing.Literal["config"]

sarvamai/requests/configure_connection_data.py

@@ -1,6 +1,7 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing_extensions
+from ..types.configure_connection_data_model import ConfigureConnectionDataModel
 from ..types.configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
 from ..types.configure_connection_data_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
 from ..types.configure_connection_data_speaker import ConfigureConnectionDataSpeaker
@@ -8,21 +9,25 @@ from ..types.configure_connection_data_target_language_code import ConfigureConn
 
 
 class ConfigureConnectionDataParams(typing_extensions.TypedDict):
+    model: typing_extensions.NotRequired[ConfigureConnectionDataModel]
+    """
+    Specifies the model to use for text-to-speech conversion.
+    - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
+    - **bulbul:v3-beta**: Advanced model with temperature control (no pitch/loudness)
+    """
+
     target_language_code: ConfigureConnectionDataTargetLanguageCode
     """
-    The language of the text is BCP-47 format
+    The language of the text in BCP-47 format
     """
 
     speaker: ConfigureConnectionDataSpeaker
     """
     The speaker voice to be used for the output audio.
     
-    **Default:** Anushka
-    
-    **Model Compatibility (Speakers compatible with respective model):**
-    - **bulbul:v2:**
-      - Female: Anushka, Manisha, Vidya, Arya
-      - Male: Abhilash, Karun, Hitesh
+    **Model Compatibility:**
+    - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
+    - **bulbul:v3-beta:** aditya (default), ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, shubh, ashutosh, advait, amelia, sophia
     
     **Note:** Speaker selection must match the chosen model version.
     """
@@ -32,13 +37,18 @@ class ConfigureConnectionDataParams(typing_extensions.TypedDict):
     Controls the pitch of the audio. Lower values result in a deeper voice, 
     while higher values make it sharper. The suitable range is between -0.75 
     and 0.75. Default is 0.0.
+    
+    **Note:** NOT supported for bulbul:v3-beta. Will be ignored if provided.
     """
 
     pace: typing_extensions.NotRequired[float]
     """
     Controls the speed of the audio. Lower values result in slower speech, 
-    while higher values make it faster. The suitable range is between 0.5 
-    and 2.0. Default is 1.0.
+    while higher values make it faster. Default is 1.0.
+    
+    **Model-specific ranges:**
+    - **bulbul:v2:** 0.3 to 3.0
+    - **bulbul:v3-beta:** 0.5 to 2.0
     """
 
     loudness: typing_extensions.NotRequired[float]
@@ -46,19 +56,38 @@ class ConfigureConnectionDataParams(typing_extensions.TypedDict):
     Controls the loudness of the audio. Lower values result in quieter audio, 
     while higher values make it louder. The suitable range is between 0.3 
     and 3.0. Default is 1.0.
+    
+    **Note:** NOT supported for bulbul:v3-beta. Will be ignored if provided.
+    """
+
+    temperature: typing_extensions.NotRequired[float]
+    """
+    Controls the randomness of the output. Lower values make the output more 
+    focused and deterministic, while higher values make it more random. 
+    The suitable range is between 0.01 and 1.0. Default is 0.6.
+    
+    **Note:** Only supported for bulbul:v3-beta. Will be ignored for bulbul:v2.
     """
 
     speech_sample_rate: typing_extensions.NotRequired[int]
     """
     Specifies the sample rate of the output audio. Supported values are 
-    8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+    8000, 16000, 22050, 24000 Hz.
+    
+    **Model-specific defaults:**
+    - **bulbul:v2:** 22050 Hz
+    - **bulbul:v3-beta:** 24000 Hz
     """
 
     enable_preprocessing: typing_extensions.NotRequired[bool]
     """
     Controls whether normalization of English words and numeric entities 
     (e.g., numbers, dates) is performed. Set to true for better handling 
-    of mixed-language text. Default is false.
+    of mixed-language text.
+    
+    **Model-specific defaults:**
+    - **bulbul:v2:** false (optional)
+    - **bulbul:v3-beta:** Always enabled (cannot be disabled)
     """
 
     output_audio_codec: typing_extensions.NotRequired[ConfigureConnectionDataOutputAudioCodec]

sarvamai/requests/doc_digitization_create_job_response.py

@@ -0,0 +1,25 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .doc_digitization_job_parameters import DocDigitizationJobParametersParams
+
+
+class DocDigitizationCreateJobResponseParams(typing_extensions.TypedDict):
+    job_id: str
+    """
+    Unique job identifier (UUID)
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage Container Type
+    """
+
+    job_parameters: DocDigitizationJobParametersParams
+    """
+    Job configuration parameters
+    """
+
+    job_state: DocDigitizationJobState

sarvamai/requests/doc_digitization_download_files_response.py

@@ -0,0 +1,37 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class DocDigitizationDownloadFilesResponseParams(typing_extensions.TypedDict):
+    """
+    Response for download-files endpoint.
+    """
+
+    job_id: str
+    """
+    Job identifier (UUID)
+    """
+
+    job_state: DocDigitizationJobState
+    """
+    Current job state
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage backend type
+    """
+
+    download_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    """
+    Map of filename to presigned download URL details
+    """
+
+    error_code: typing_extensions.NotRequired[str]
+    error_message: typing_extensions.NotRequired[str]

sarvamai/requests/doc_digitization_error_details.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.doc_digitization_error_code import DocDigitizationErrorCode
+
+
+class DocDigitizationErrorDetailsParams(typing_extensions.TypedDict):
+    message: str
+    """
+    Message describing the error
+    """
+
+    code: DocDigitizationErrorCode
+    """
+    Error code for the specific error that has occurred.
+    """
+
+    request_id: typing_extensions.NotRequired[str]
+    """
+    Unique identifier for the request. Format: date_UUID4
+    """

sarvamai/requests/doc_digitization_error_message.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from .doc_digitization_error_details import DocDigitizationErrorDetailsParams
+
+
+class DocDigitizationErrorMessageParams(typing_extensions.TypedDict):
+    error: DocDigitizationErrorDetailsParams
+    """
+    Error details
+    """

sarvamai/requests/doc_digitization_job_detail.py

@@ -0,0 +1,64 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_detail_state import DocDigitizationJobDetailState
+from .doc_digitization_page_error import DocDigitizationPageErrorParams
+from .task_file_details import TaskFileDetailsParams
+
+
+class DocDigitizationJobDetailParams(typing_extensions.TypedDict):
+    """
+    Processing details for a single input file with page-level metrics.
+    """
+
+    inputs: typing.Sequence[TaskFileDetailsParams]
+    """
+    Input file(s) for this task
+    """
+
+    outputs: typing.Sequence[TaskFileDetailsParams]
+    """
+    Output file(s) produced
+    """
+
+    state: DocDigitizationJobDetailState
+    """
+    Processing state for this file
+    """
+
+    total_pages: typing_extensions.NotRequired[int]
+    """
+    Total pages/images in the input file
+    """
+
+    pages_processed: typing_extensions.NotRequired[int]
+    """
+    Number of pages processed so far
+    """
+
+    pages_succeeded: typing_extensions.NotRequired[int]
+    """
+    Number of pages successfully processed
+    """
+
+    pages_failed: typing_extensions.NotRequired[int]
+    """
+    Number of pages that failed processing
+    """
+
+    error_message: typing_extensions.NotRequired[str]
+    """
+    Error message if processing failed
+    """
+
+    error_code: typing_extensions.NotRequired[str]
+    """
+    Standardized error code if failed
+    """
+
+    page_errors: typing_extensions.NotRequired[typing.Sequence[DocDigitizationPageErrorParams]]
+    """
+    Detailed errors for each failed page
+    """

sarvamai/requests/doc_digitization_job_parameters.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.doc_digitization_output_format import DocDigitizationOutputFormat
+from ..types.doc_digitization_supported_language import DocDigitizationSupportedLanguage
+
+
+class DocDigitizationJobParametersParams(typing_extensions.TypedDict):
+    """
+    Job parameters for document digitization.
+    """
+
+    language: typing_extensions.NotRequired[DocDigitizationSupportedLanguage]
+    """
+    ISO language code for the document
+    """
+
+    output_format: typing_extensions.NotRequired[DocDigitizationOutputFormat]
+    """
+    Output format: html or md
+    """

sarvamai/requests/doc_digitization_job_status_response.py

@@ -0,0 +1,65 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .doc_digitization_job_detail import DocDigitizationJobDetailParams
+
+
+class DocDigitizationJobStatusResponseParams(typing_extensions.TypedDict):
+    """
+    Response model for job status endpoint.
+    """
+
+    job_id: str
+    """
+    Job identifier (UUID)
+    """
+
+    job_state: DocDigitizationJobState
+    """
+    Current job state
+    """
+
+    created_at: dt.datetime
+    """
+    Job creation timestamp (ISO 8601)
+    """
+
+    updated_at: dt.datetime
+    """
+    Last update timestamp (ISO 8601)
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage backend type
+    """
+
+    total_files: typing_extensions.NotRequired[int]
+    """
+    Total input files (always 1)
+    """
+
+    successful_files_count: typing_extensions.NotRequired[int]
+    """
+    Files that completed successfully
+    """
+
+    failed_files_count: typing_extensions.NotRequired[int]
+    """
+    Files that failed
+    """
+
+    error_message: typing_extensions.NotRequired[str]
+    """
+    Job-level error message
+    """
+
+    job_details: typing_extensions.NotRequired[typing.Sequence[DocDigitizationJobDetailParams]]
+    """
+    Per-file processing details with page metrics
+    """

sarvamai/requests/doc_digitization_page_error.py

@@ -0,0 +1,24 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class DocDigitizationPageErrorParams(typing_extensions.TypedDict):
+    """
+    Error details for a specific page.
+    """
+
+    page_number: int
+    """
+    Page number that failed
+    """
+
+    error_code: str
+    """
+    Standardized error code
+    """
+
+    error_message: str
+    """
+    Human-readable error description
+    """

sarvamai/requests/doc_digitization_upload_files_response.py

@@ -0,0 +1,34 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.doc_digitization_job_state import DocDigitizationJobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class DocDigitizationUploadFilesResponseParams(typing_extensions.TypedDict):
+    """
+    Response with presigned upload URLs
+    """
+
+    job_id: str
+    """
+    Job identifier
+    """
+
+    job_state: DocDigitizationJobState
+    """
+    Current job state
+    """
+
+    upload_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    """
+    Map of filename to presigned upload URL details
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage backend type
+    """

sarvamai/requests/doc_digitization_webhook_callback.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class DocDigitizationWebhookCallbackParams(typing_extensions.TypedDict):
+    """
+    Webhook configuration for job completion notification
+    """
+
+    url: str
+    """
+    HTTPS webhook URL to call upon job completion (HTTP not allowed)
+    """
+
+    auth_token: typing_extensions.NotRequired[str]
+    """
+    Authorization token sent as X-SARVAM-JOB-CALLBACK-TOKEN header
+    """

sarvamai/requests/speech_to_text_job_parameters.py

@@ -1,6 +1,7 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing_extensions
+from ..types.mode import Mode
 from ..types.speech_to_text_model import SpeechToTextModel
 from ..types.speech_to_text_translate_language import SpeechToTextTranslateLanguage
 
@@ -8,12 +9,52 @@ from ..types.speech_to_text_translate_language import SpeechToTextTranslateLangu
 class SpeechToTextJobParametersParams(typing_extensions.TypedDict):
     language_code: typing_extensions.NotRequired[SpeechToTextTranslateLanguage]
     """
-    Language code
+    Specifies the language of the input audio in BCP-47 format.
+    
+    **Available Options:**
+    - `unknown` (default): Use when the language is not known; the API will auto-detect.
+    - `hi-IN`: Hindi
+    - `bn-IN`: Bengali
+    - `kn-IN`: Kannada
+    - `ml-IN`: Malayalam
+    - `mr-IN`: Marathi
+    - `od-IN`: Odia
+    - `pa-IN`: Punjabi
+    - `ta-IN`: Tamil
+    - `te-IN`: Telugu
+    - `en-IN`: English
+    - `gu-IN`: Gujarati
     """
 
     model: typing_extensions.NotRequired[SpeechToTextModel]
     """
-    Model to be used for speech to text
+    Model to be used for speech to text.
+    
+    - **saarika:v2.5** (default): Transcribes audio in the spoken language.
+    
+    - **saaras:v3**: State-of-the-art model with flexible output formats. Supports multiple modes via the `mode` parameter: transcribe, translate, verbatim, translit, codemix.
+    """
+
+    mode: typing_extensions.NotRequired[Mode]
+    """
+    Mode of operation. **Only applicable when using saaras:v3 model.**
+    
+    Example audio: 'मेरा फोन नंबर है 9840950950'
+    
+    - **transcribe** (default): Standard transcription in the original language with proper formatting and number normalization.
+      - Output: `मेरा फोन नंबर है 9840950950`
+    
+    - **translate**: Translates speech from any supported Indic language to English.
+      - Output: `My phone number is 9840950950`
+    
+    - **verbatim**: Exact word-for-word transcription without normalization, preserving filler words and spoken numbers as-is.
+      - Output: `मेरा फोन नंबर है नौ आठ चार zero नौ पांच zero नौ पांच zero`
+    
+    - **translit**: Romanization - Transliterates speech to Latin/Roman script only.
+      - Output: `mera phone number hai 9840950950`
+    
+    - **codemix**: Code-mixed text with English words in English and Indic words in native script.
+      - Output: `मेरा phone number है 9840950950`
     """
 
     with_timestamps: typing_extensions.NotRequired[bool]

sarvamai/requests/speech_to_text_translate_job_parameters.py

@@ -12,7 +12,10 @@ class SpeechToTextTranslateJobParametersParams(typing_extensions.TypedDict):
 
     model: typing_extensions.NotRequired[SpeechToTextTranslateModel]
     """
-    Model to be used for converting speech to text in target language
+    Model to be used for speech to text translation.
+    
+    - **saaras:v2.5** (default): Translation model that translates audio from any spoken Indic language to English.
+      - Example: Hindi audio → English text output
     """
 
     with_diarization: typing_extensions.NotRequired[bool]