sarvamai 0.1.6__tar.gz → 0.1.7__tar.gz

sarvamai-0.1.7/PKG-INFO

@@ -0,0 +1,1192 @@
+Metadata-Version: 2.1
+Name: sarvamai
+Version: 0.1.7
+Summary: 
+Requires-Python: >=3.8,<4.0
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: OS Independent
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Dist: httpx (>=0.21.2)
+Requires-Dist: pydantic (>=1.9.2)
+Requires-Dist: pydantic-core (>=2.18.2,<3.0.0)
+Requires-Dist: typing_extensions (>=4.0.0)
+Requires-Dist: websockets (==12.0)
+Description-Content-Type: text/markdown
+
+# Sarvam Python Library
+
+[![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-Built%20with%20Fern-brightgreen)](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2Fsarvamai%2Fsarvam-python-sdk)
+[![pypi](https://img.shields.io/pypi/v/sarvamai)](https://pypi.python.org/pypi/sarvamai)
+
+The Sarvam Python library provides convenient access to the Sarvam API from Python.
+
+## Documentation
+
+API reference documentation is available [here](https://www.sarvam.ai/).
+
+## Installation
+
+```sh
+pip install sarvamai
+```
+
+## Reference
+
+A full reference for this library is available [here](#References).
+
+## Usage
+
+Instantiate and use the client with the following:
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.text.translate(
+    input="input",
+    source_language_code="auto",
+    target_language_code="bn-IN",
+)
+```
+
+## Async Client
+
+The SDK also exports an `async` client so that you can make non-blocking calls to our API.
+
+```python
+import asyncio
+
+from sarvamai import AsyncSarvamAI
+
+client = AsyncSarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+
+
+async def main() -> None:
+    await client.text.translate(
+        input="input",
+        source_language_code="auto",
+        target_language_code="bn-IN",
+    )
+
+
+asyncio.run(main())
+```
+
+## Exception Handling
+
+When the API returns a non-success status code (4xx or 5xx response), a subclass of the following error
+will be thrown.
+
+```python
+from sarvamai.core.api_error import ApiError
+
+try:
+    client.text.translate(...)
+except ApiError as e:
+    print(e.status_code)
+    print(e.body)
+```
+
+## Advanced
+
+### Retries
+
+The SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long
+as the request is deemed retryable and the number of retry attempts has not grown larger than the configured
+retry limit (default: 2).
+
+A request is deemed retryable when any of the following HTTP status codes is returned:
+
+- [408](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/408) (Timeout)
+- [429](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429) (Too Many Requests)
+- [5XX](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500) (Internal Server Errors)
+
+Use the `max_retries` request option to configure this behavior.
+
+```python
+client.text.translate(..., request_options={
+    "max_retries": 1
+})
+```
+
+### Timeouts
+
+The SDK defaults to a 60 second timeout. You can configure this with a timeout option at the client or request level.
+
+```python
+
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    ...,
+    timeout=20.0,
+)
+
+
+# Override timeout for a specific method
+client.text.translate(..., request_options={
+    "timeout_in_seconds": 1
+})
+```
+
+### Custom Client
+
+You can override the `httpx` client to customize it for your use-case. Some common use-cases include support for proxies
+and transports.
+
+```python
+import httpx
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    ...,
+    httpx_client=httpx.Client(
+        proxies="http://my.test.proxy.example.com",
+        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
+    ),
+)
+```
+
+## Contributing
+
+While we value open-source contributions to this SDK, this library is generated programmatically.
+Additions made directly to this library would have to be moved over to our generation code,
+otherwise they would be overwritten upon the next generated release. Feel free to open a PR as
+a proof of concept, but know that we will not be able to merge it as-is. We suggest opening
+an issue first to discuss with us!
+
+On the other hand, contributions to the README are always very welcome!
+
+---
+
+## References
+
+### Text
+<details><summary><code>client.text.<a href="src/sarvamai/text/client.py">translate</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**Translation** converts text from one language to another while preserving its meaning.
+For Example: **'मैं ऑफिस जा रहा हूँ'** translates to **'I am going to the office'** in English, where the script and language change, but the original meaning remains the same.
+
+Available languages:
+- **`bn-IN`**: Bengali
+- **`en-IN`**: English
+- **`gu-IN`**: Gujarati
+- **`hi-IN`**: Hindi
+- **`kn-IN`**: Kannada
+- **`ml-IN`**: Malayalam
+- **`mr-IN`**: Marathi
+- **`od-IN`**: Odia
+- **`pa-IN`**: Punjabi
+- **`ta-IN`**: Tamil
+- **`te-IN`**: Telugu
+
+#### Newly added languages:
+- **`as-IN`**: Assamese
+- **`brx-IN`**: Bodo
+- **`doi-IN`**: Dogri
+- **`kok-IN`**: Konkani
+- **`ks-IN`**: Kashmiri
+- **`mai-IN`**: Maithili
+- **`mni-IN`**: Manipuri (Meiteilon)
+- **`ne-IN`**: Nepali
+- **`sa-IN`**: Sanskrit
+- **`sat-IN`**: Santali
+- **`sd-IN`**: Sindhi
+- **`ur-IN`**: Urdu
+
+For hands-on practice, you can explore the notebook tutorial on [Translate API Tutorial](https://github.com/sarvamai/sarvam-ai-cookbook/blob/main/notebooks/translate/Translate_API_Tutorial.ipynb).
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.text.translate(
+    input="input",
+    source_language_code="auto",
+    target_language_code="bn-IN",
+)
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**input:** `str` — The text you want to translate is the input text that will be processed by the translation model. The maximum is 1000 characters for Mayura:v1 and 2000 characters for Sarvam-Translate:v1.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**source_language_code:** `TranslateSourceLanguage` 
+
+Source language code for translation input.
+
+**mayura:v1 Languages:** Bengali, English, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu
+
+**sarvam-translate:v1 Languages:** All mayura:v1 languages and Assamese, Bodo, Dogri, Konkani, Kashmiri, Maithili, Manipuri, Nepali, Sanskrit, Santali, Sindhi, Urdu
+
+**Note:** mayura:v1 supports automatic language detection using 'auto' as the source language code.
+
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**target_language_code:** `TranslateTargetLanguage` 
+
+The language code of the translated text. This specifies the target language for translation.
+
+**mayura:v1 Languages:** Bengali, English, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu
+
+**sarvam-translate:v1 Languages:** All mayura:v1 and Assamese, Bodo, Dogri, Konkani, Kashmiri, Maithili, Manipuri, Nepali, Sanskrit, Santali, Sindhi, Urdu
+
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**speaker_gender:** `typing.Optional[TranslateSpeakerGender]` — Please specify the gender of the speaker for better translations.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**mode:** `typing.Optional[TranslateMode]` 
+
+Specifies the tone or style of the translation.
+
+**Model Support:**
+- **mayura:v1**: Supports formal, classic-colloquial, and modern-colloquial modes
+- **sarvam-translate:v1**: Only formal mode is supported
+
+**Default:** formal
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**model:** `typing.Optional[TranslateModel]` 
+
+Specifies the translation model to use.
+- mayura:v1: Supports 12 languages with all modes, output scripts, and automatic language detection.
+- sarvam-translate:v1: Supports all 22 scheduled languages of India, formal mode only.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**enable_preprocessing:** `typing.Optional[bool]` 
+
+This will enable custom preprocessing of the input text which can result in better translations.
+ Recommendation- You can switch on whenever there is some complex text with difficult vocabulary and sentences, for which you want simple translations that people can understand.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**output_script:** `typing.Optional[TransliterateMode]` 
+
+**output_script**: This is an optional parameter which controls the transliteration style applied to the output text.
+
+**Transliteration**: Converting text from one script to another while preserving pronunciation.
+
+For mayura:v1 - We support transliteration with four options:
+- **`null`**(default): No transliteration applied.
+- **`roman`**: Transliteration in Romanized script.
+- **`fully-native`**: Transliteration in the native script with formal style.
+- **`spoken-form-in-native`**: Transliteration in the native script with spoken style.
+
+For sarvam-translate:v1 - Transliteration is not supported.
+#### Example:
+English: Your EMI of Rs. 3000 is pending.
+Default modern translation: आपका Rs. 3000 का EMI pending है (when `null` is passed).
+
+With postprocessing enabled:
+- **roman output**: aapka Rs. 3000 ka EMI pending hai.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**numerals_format:** `typing.Optional[NumeralsFormat]` 
+
+`numerals_format` is an optional parameter with two options (supported for both mayura:v1 and sarvam-translate:v1):
+
+- **`international`** (default): Uses regular numerals (0-9).
+- **`native`**: Uses language-specific native numerals.
+
+#### Example:
+- If `international` format is selected, we use regular numerals (0-9). For example: `मेरा phone number है: 9840950950`.
+- If `native` format is selected, we use language-specific native numerals, like: `मेरा phone number है: ९८४०९५०९५०`.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+    
+</dd>
+</dl>
+</dd>
+</dl>
+
+
+</dd>
+</dl>
+</details>
+
+<details><summary><code>client.text.<a href="src/sarvamai/text/client.py">identify_language</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+Identifies the language (e.g., en-IN, hi-IN) and script (e.g., Latin, Devanagari) of the input text, supporting multiple languages.
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.text.identify_language(
+    input="input",
+)
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**input:** `str` — The text input for language and script identification.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+    
+</dd>
+</dl>
+</dd>
+</dl>
+
+
+</dd>
+</dl>
+</details>
+
+<details><summary><code>client.text.<a href="src/sarvamai/text/client.py">transliterate</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**Transliteration** converts text from one script to another while preserving the original pronunciation. For example, **'नमस्ते'** becomes **'namaste'** in English, and **'how are you'** can be written as **'हाउ आर यू'** in Devanagari. This process ensures that the sound of the original text remains intact, even when written in a different script.
+
+Transliteration is useful when you want to represent words phonetically across different writing systems, such as converting **'मैं ऑफिस जा रहा हूँ'** to **'main office ja raha hun'** in English letters.
+
+**Translation**, on the other hand, converts text from one language to another while preserving the meaning rather than pronunciation. For example, **'मैं ऑफिस जा रहा हूँ'** translates to **'I am going to the office'** in English, changing both the script and the language while conveying the intended message.
+#### Examples of **Transliteration**:
+- **'Good morning'** becomes **'गुड मॉर्निंग'** in Hindi, where the pronunciation is preserved but the meaning is not translated.
+- **'सुप्रभात'** becomes **'suprabhat'** in English.
+
+Available languages:
+- **`en-IN`**: English
+- **`hi-IN`**: Hindi
+- **`bn-IN`**: Bengali
+- **`gu-IN`**: Gujarati
+- **`kn-IN`**: Kannada
+- **`ml-IN`**: Malayalam
+- **`mr-IN`**: Marathi
+- **`od-IN`**: Odia
+- **`pa-IN`**: Punjabi
+- **`ta-IN`**: Tamil
+- **`te-IN`**: Telugu
+
+For hands-on practice, you can explore the notebook tutorial on [Transliterate API Tutorial](https://github.com/sarvamai/sarvam-ai-cookbook/blob/main/notebooks/transliterate/Transliterate_API_Tutorial.ipynb).
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.text.transliterate(
+    input="input",
+    source_language_code="auto",
+    target_language_code="bn-IN",
+)
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**input:** `str` — The text you want to transliterate.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**source_language_code:** `TransliterateSourceLanguage` 
+
+The language code of the input text. This specifies the source language for transliteration.
+
+
+
+ Note:  The source language should either be an Indic language or English. As we supports both Indic-to-English and English-to-Indic transliteration.
+
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**target_language_code:** `TranslatiterateTargetLanguage` 
+
+The language code of the transliteration text. This specifies the target language for transliteration.
+
+
+
+ Note:The target language should either be an Indic language or English. As we supports both Indic-to-English and English-to-Indic transliteration.
+
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**numerals_format:** `typing.Optional[NumeralsFormat]` 
+
+`numerals_format` is an optional parameter with two options:
+
+- **`international`** (default): Uses regular numerals (0-9).
+- **`native`**: Uses language-specific native numerals.
+
+#### Example:
+- If `international` format is selected, we use regular numerals (0-9). For example: `मेरा phone number है: 9840950950`.
+- If `native` format is selected, we use language-specific native numerals, like: `मेरा phone number है: ९८४०९५०९५०`.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**spoken_form_numerals_language:** `typing.Optional[SpokenFormNumeralsFormat]` 
+
+`spoken_form_numerals_language` is an optional parameter with two options and only works when spoken_form is true:
+
+- **`english`** : Numbers in the text will be spoken in English.
+- **`native(default)`**: Numbers in the text will be spoken in the native language.
+
+#### Examples:
+- **Input:** "मेरे पास ₹200 है"
+  - If `english` format is selected: "मेरे पास टू हन्डर्ड रूपीस है"
+  - If `native` format is selected: "मेरे पास दो सौ रुपये है"
+
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**spoken_form:** `typing.Optional[bool]` 
+
+  - Default: `False`
+  - Converts text into a natural spoken form when `True`.
+  - **Note:** No effect if output language is `en-IN`.
+
+#### Example:
+- **Input:** `मुझे कल 9:30am को appointment है`
+  - **Output:** `मुझे कल सुबह साढ़े नौ बजे को अपॉइंटमेंट है`
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+    
+</dd>
+</dl>
+</dd>
+</dl>
+
+
+</dd>
+</dl>
+</details>
+
+### SpeechToText
+<details><summary><code>client.speech_to_text.<a href="src/sarvamai/speech_to_text/client.py">transcribe</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+### Real-Time Speech to Text API
+
+This API transcribes speech to text in multiple Indian languages and English. Supports real-time transcription for interactive applications.
+
+#### Available Options:
+- **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+- **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt/stt-batch-api)
+  - Supports diarization (speaker identification)
+
+#### Note:
+- Pricing differs for Real-Time and Batch APIs
+- Diarization is only available in Batch API with separate pricing
+- Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.speech_to_text.transcribe()
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**file:** `from __future__ import annotations
+
+core.File` — See core.File for more documentation
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**model:** `typing.Optional[SpeechToTextModel]` 
+
+Specifies the model to use for speech-to-text conversion.
+Note:- Default model is `saarika:v2`
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**language_code:** `typing.Optional[SpeechToTextLanguage]` 
+
+Specifies the language of the input audio. This parameter is required to ensure accurate transcription.
+ For the `saarika:v1` model, this parameter is mandatory.
+ For the `saarika:v2` model, it is optional.
+`unknown`: Use this when the language is not known; the API will detect it automatically. 
+Note:- that the `saarika:v1` model does not support `unknown` language code.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+    
+</dd>
+</dl>
+</dd>
+</dl>
+
+
+</dd>
+</dl>
+</details>
+
+<details><summary><code>client.speech_to_text.<a href="src/sarvamai/speech_to_text/client.py">translate</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+### Real-Time Speech to Text Translation API
+
+This API automatically detects the input language, transcribes the speech, and translates the text to English.
+
+#### Available Options:
+- **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+- **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt-translate/stt-translate-batch-api)
+  - Supports diarization (speaker identification)
+
+#### Note:
+- Pricing differs for Real-Time and Batch APIs
+- Diarization is only available in Batch API with separate pricing
+- Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.speech_to_text.translate()
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**file:** `from __future__ import annotations
+
+core.File` — See core.File for more documentation
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**prompt:** `typing.Optional[str]` — Conversation context can be passed as a prompt to boost model accuracy. However, the current system is at an experimentation stage and doesn’t match the prompt performance of large language models.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**model:** `typing.Optional[SpeechToTextTranslateModel]` — Model to be used for converting speech to text in target language
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+    
+</dd>
+</dl>
+</dd>
+</dl>
+
+
+</dd>
+</dl>
+</details>
+
+### TextToSpeech
+<details><summary><code>client.text_to_speech.<a href="src/sarvamai/text_to_speech/client.py">convert</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+This is the model to convert text into spoken audio. 
+The output is a wave file encoded as a base64 string.
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.text_to_speech.convert(
+    text="text",
+    target_language_code="bn-IN",
+)
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**text:** `str` 
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**target_language_code:** `TextToSpeechLanguage` — The language of the text is BCP-47 format
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**speaker:** `typing.Optional[TextToSpeechSpeaker]` 
+
+The speaker voice to be used for the output audio.
+
+**Default:** Meera
+
+**Model Compatibility (Speakers compatible with respective models):**
+- **bulbul:v1:**
+  - Female: Diya, Maya, Meera, Pavithra, Maitreyi, Misha
+  - Male: Amol, Arjun, Amartya, Arvind, Neel, Vian
+
+- **bulbul:v2:**
+  - Female: Anushka, Manisha, Vidya, Arya
+  - Male: Abhilash, Karun, Hitesh
+
+**Note:** Speaker selection must match the chosen model version.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**pitch:** `typing.Optional[float]` — 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.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**pace:** `typing.Optional[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.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**loudness:** `typing.Optional[float]` — 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.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**speech_sample_rate:** `typing.Optional[SpeechSampleRate]` — Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**enable_preprocessing:** `typing.Optional[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.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**model:** `typing.Optional[TextToSpeechModel]` — Specifies the model to use for text-to-speech conversion. Default is bulbul:v1.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+    
+</dd>
+</dl>
+</dd>
+</dl>
+
+
+</dd>
+</dl>
+</details>
+
+### Chat
+<details><summary><code>client.chat.<a href="src/sarvamai/chat/client.py">completions</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+Calls Sarvam LLM API to get the chat completion. Supported model(s): `sarvam-m`.
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.chat.completions(
+    messages=[{"content": "content", "role": "assistant"}],
+)
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**messages:** `typing.Sequence[ChatCompletionRequestMessageParams]` — A list of messages comprising the conversation so far.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**temperature:** `typing.Optional[float]` 
+
+What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
+We generally recommend altering this or `top_p` but not both.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**top_p:** `typing.Optional[float]` 
+
+An alternative to sampling with temperature, called nucleus sampling,
+where the model considers the results of the tokens with top_p probability
+mass. So 0.1 means only the tokens comprising the top 10% probability mass
+are considered.
+
+We generally recommend altering this or `temperature` but not both.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**reasoning_effort:** `typing.Optional[ReasoningEffort]` 
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**max_tokens:** `typing.Optional[int]` — The maximum number of tokens that can be generated in the chat completion.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**stream:** `typing.Optional[bool]` 
+
+If set to true, the model response data will be streamed to the client
+as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**stop:** `typing.Optional[StopConfigurationParams]` 
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**n:** `typing.Optional[int]` — How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**seed:** `typing.Optional[int]` 
+
+This feature is in Beta.
+If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.
+Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**frequency_penalty:** `typing.Optional[float]` 
+
+Number between -2.0 and 2.0. Positive values penalize new tokens based on
+their existing frequency in the text so far, decreasing the model's
+likelihood to repeat the same line verbatim.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**presence_penalty:** `typing.Optional[float]` 
+
+Number between -2.0 and 2.0. Positive values penalize new tokens based on
+whether they appear in the text so far, increasing the model's likelihood
+to talk about new topics.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**wiki_grounding:** `typing.Optional[bool]` — If this parameter is enabled, then the model uses a RAG based approach to retrieve relevant chunks from Wikipedia and uses them to answer the question. This is particularly useful for queries seeking factual information.
+    
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+    
+</dd>
+</dl>
+</dd>
+</dl>
+
+
+</dd>
+</dl>
+</details>
+