cartesia 2.0.5__tar.gz → 2.0.7__tar.gz

cartesia-2.0.7/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

{cartesia-2.0.5 → cartesia-2.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: cartesia
-Version: 2.0.5
+Version: 2.0.7
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers
@@ -16,6 +16,7 @@ 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: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
 Requires-Dist: aiohttp (>=3.10.10)
@@ -28,6 +29,7 @@ Requires-Dist: pydantic-core (>=2.18.2,<3.0.0)
 Requires-Dist: pydub (>=0.25.1)
 Requires-Dist: typing_extensions (>=4.0.0)
 Requires-Dist: websockets (>=10.4)
+Project-URL: Repository, https://github.com/cartesia-ai/cartesia-python
 Description-Content-Type: text/markdown
 
 # Cartesia Python Library
@@ -230,12 +232,14 @@ with open("path/to/audio.wav", "rb") as f:
 chunk_size = 640
 audio_chunks = [audio_data[i:i+chunk_size] for i in range(0, len(audio_data), chunk_size)]
 
-# Create websocket connection
+# Create websocket connection with endpointing parameters
 ws = client.stt.websocket(
-    model="ink-whisper",
-    language="en",           # Must match the language of your audio
-    encoding="pcm_s16le",    # Must match your audio's encoding format
-    sample_rate=16000,       # Must match your audio's sample rate
+    model="ink-whisper",                 # Model (required)
+    language="en",                       # Language of your audio (required)
+    encoding="pcm_s16le",                # Audio encoding format (required)
+    sample_rate=16000,                   # Audio sample rate (required)
+    min_volume=0.1,                      # Volume threshold for voice activity detection
+    max_silence_duration_secs=0.4,       # Maximum silence duration before endpointing
 )
 
 # Send audio chunks (streaming approach)
@@ -246,10 +250,20 @@ for chunk in audio_chunks:
 ws.send("finalize")
 ws.send("done")
 
-# Receive transcription results
+# Receive transcription results with word-level timestamps
 for result in ws.receive():
     if result['type'] == 'transcript':
         print(f"Transcription: {result['text']}")
+        
+        # Handle word-level timestamps if available
+        if 'words' in result and result['words']:
+            print("Word-level timestamps:")
+            for word_info in result['words']:
+                word = word_info['word']
+                start = word_info['start']
+                end = word_info['end']
+                print(f"  '{word}': {start:.2f}s - {end:.2f}s")
+        
         if result['is_final']:
             print("Final result received")
     elif result['type'] == 'done':
@@ -270,17 +284,20 @@ from cartesia import AsyncCartesia
 async def streaming_stt_example():
     """
     Advanced async STT example for real-time streaming applications.
-    This example simulates streaming audio processing with proper error handling.
+    This example simulates streaming audio processing with proper error handling
+    and demonstrates the new endpointing and word timestamp features.
     """
     client = AsyncCartesia(api_key=os.getenv("CARTESIA_API_KEY"))
     
     try:
-        # Create websocket connection
+        # Create websocket connection with voice activity detection
         ws = await client.stt.websocket(
-            model="ink-whisper",
-            language="en",           # Must match the language of your audio
-            encoding="pcm_s16le",    # Must match your audio's encoding format
-            sample_rate=16000,       # Must match your audio's sample rate
+            model="ink-whisper",             # Model (required)
+            language="en",                   # Language of your audio (required)
+            encoding="pcm_s16le",            # Audio encoding format (required)
+            sample_rate=16000,               # Audio sample rate (required)
+            min_volume=0.15,                 # Volume threshold for voice activity detection
+            max_silence_duration_secs=0.3,   # Maximum silence duration before endpointing
         )
         
         # Simulate streaming audio data (replace with your audio source)
@@ -319,8 +336,9 @@ async def streaming_stt_example():
                 print(f"Error sending audio: {e}")
         
         async def receive_transcripts():
-            """Receive and process transcription results"""
+            """Receive and process transcription results with word timestamps"""
             full_transcript = ""
+            all_word_timestamps = []
             
             try:
                 async for result in ws.receive():
@@ -328,6 +346,19 @@ async def streaming_stt_example():
                         text = result['text']
                         is_final = result['is_final']
                         
+                        # Handle word-level timestamps
+                        if 'words' in result and result['words']:
+                            word_timestamps = result['words']
+                            all_word_timestamps.extend(word_timestamps)
+                            
+                            if is_final:
+                                print("Word-level timestamps:")
+                                for word_info in word_timestamps:
+                                    word = word_info['word']
+                                    start = word_info['start']
+                                    end = word_info['end']
+                                    print(f"  '{word}': {start:.2f}s - {end:.2f}s")
+                        
                         if is_final:
                             # Final result - this text won't change
                             full_transcript += text + " "
@@ -343,17 +374,18 @@ async def streaming_stt_example():
             except Exception as e:
                 print(f"Error receiving transcripts: {e}")
             
-            return full_transcript.strip()
+            return full_transcript.strip(), all_word_timestamps
         
         print("Starting streaming STT...")
         
         # Use asyncio.gather to run audio sending and transcript receiving concurrently
-        _, final_transcript = await asyncio.gather(
+        _, (final_transcript, word_timestamps) = await asyncio.gather(
             send_audio(),
             receive_transcripts()
         )
         
         print(f"\nComplete transcript: {final_transcript}")
+        print(f"Total words with timestamps: {len(word_timestamps)}")
         
         # Clean up
         await ws.close()
@@ -368,6 +400,73 @@ if __name__ == "__main__":
     asyncio.run(streaming_stt_example())
 ```
 
+## Batch Speech-to-Text (STT)
+
+For processing pre-recorded audio files, use the batch STT API which supports uploading complete audio files for transcription:
+
+```python
+from cartesia import Cartesia
+import os
+
+client = Cartesia(api_key=os.getenv("CARTESIA_API_KEY"))
+
+# Transcribe an audio file with word-level timestamps
+with open("path/to/audio.wav", "rb") as audio_file:
+    response = client.stt.transcribe(
+        file=audio_file,                    # Audio file to transcribe
+        model="ink-whisper",                # STT model (required)
+        language="en",                      # Language of the audio (optional)
+        timestamp_granularities=["word"],   # Include word-level timestamps (optional)
+        encoding="pcm_s16le",               # Audio encoding (optional)
+        sample_rate=16000,                  # Audio sample rate (optional)
+    )
+
+# Access transcription results
+print(f"Transcribed text: {response.text}")
+print(f"Audio duration: {response.duration:.2f} seconds")
+
+# Process word-level timestamps if requested
+if response.words:
+    print("\nWord-level timestamps:")
+    for word_info in response.words:
+        word = word_info.word
+        start = word_info.start
+        end = word_info.end
+        print(f"  '{word}': {start:.2f}s - {end:.2f}s")
+```
+
+### Async Batch STT
+
+```python
+import asyncio
+from cartesia import AsyncCartesia
+import os
+
+async def transcribe_file():
+    client = AsyncCartesia(api_key=os.getenv("CARTESIA_API_KEY"))
+    
+    with open("path/to/audio.wav", "rb") as audio_file:
+        response = await client.stt.transcribe(
+            file=audio_file,
+            model="ink-whisper",
+            language="en",
+            timestamp_granularities=["word"],
+        )
+    
+    print(f"Transcribed text: {response.text}")
+    
+    # Process word timestamps
+    if response.words:
+        for word_info in response.words:
+            print(f"'{word_info.word}': {word_info.start:.2f}s - {word_info.end:.2f}s")
+    
+    await client.close()
+
+asyncio.run(transcribe_file())
+```
+
+> **Note:** Batch STT also supports OpenAI's audio transcriptions format for easy migration from OpenAI Whisper. See our [migration guide](https://docs.cartesia.ai/api-reference/stt/migrate-from-open-ai) for details.
+
 ## Voices
 
 List all available Voices with `client.voices.list`, which returns an iterable that automatically handles pagination:

{cartesia-2.0.5 → cartesia-2.0.7}/README.md

@@ -198,12 +198,14 @@ with open("path/to/audio.wav", "rb") as f:
 chunk_size = 640
 audio_chunks = [audio_data[i:i+chunk_size] for i in range(0, len(audio_data), chunk_size)]
 
-# Create websocket connection
+# Create websocket connection with endpointing parameters
 ws = client.stt.websocket(
-    model="ink-whisper",
-    language="en",           # Must match the language of your audio
-    encoding="pcm_s16le",    # Must match your audio's encoding format
-    sample_rate=16000,       # Must match your audio's sample rate
+    model="ink-whisper",                 # Model (required)
+    language="en",                       # Language of your audio (required)
+    encoding="pcm_s16le",                # Audio encoding format (required)
+    sample_rate=16000,                   # Audio sample rate (required)
+    min_volume=0.1,                      # Volume threshold for voice activity detection
+    max_silence_duration_secs=0.4,       # Maximum silence duration before endpointing
 )
 
 # Send audio chunks (streaming approach)
@@ -214,10 +216,20 @@ for chunk in audio_chunks:
 ws.send("finalize")
 ws.send("done")
 
-# Receive transcription results
+# Receive transcription results with word-level timestamps
 for result in ws.receive():
     if result['type'] == 'transcript':
         print(f"Transcription: {result['text']}")
+        
+        # Handle word-level timestamps if available
+        if 'words' in result and result['words']:
+            print("Word-level timestamps:")
+            for word_info in result['words']:
+                word = word_info['word']
+                start = word_info['start']
+                end = word_info['end']
+                print(f"  '{word}': {start:.2f}s - {end:.2f}s")
+        
         if result['is_final']:
             print("Final result received")
     elif result['type'] == 'done':
@@ -238,17 +250,20 @@ from cartesia import AsyncCartesia
 async def streaming_stt_example():
     """
     Advanced async STT example for real-time streaming applications.
-    This example simulates streaming audio processing with proper error handling.
+    This example simulates streaming audio processing with proper error handling
+    and demonstrates the new endpointing and word timestamp features.
     """
     client = AsyncCartesia(api_key=os.getenv("CARTESIA_API_KEY"))
     
     try:
-        # Create websocket connection
+        # Create websocket connection with voice activity detection
         ws = await client.stt.websocket(
-            model="ink-whisper",
-            language="en",           # Must match the language of your audio
-            encoding="pcm_s16le",    # Must match your audio's encoding format
-            sample_rate=16000,       # Must match your audio's sample rate
+            model="ink-whisper",             # Model (required)
+            language="en",                   # Language of your audio (required)
+            encoding="pcm_s16le",            # Audio encoding format (required)
+            sample_rate=16000,               # Audio sample rate (required)
+            min_volume=0.15,                 # Volume threshold for voice activity detection
+            max_silence_duration_secs=0.3,   # Maximum silence duration before endpointing
         )
         
         # Simulate streaming audio data (replace with your audio source)
@@ -287,8 +302,9 @@ async def streaming_stt_example():
                 print(f"Error sending audio: {e}")
         
         async def receive_transcripts():
-            """Receive and process transcription results"""
+            """Receive and process transcription results with word timestamps"""
             full_transcript = ""
+            all_word_timestamps = []
             
             try:
                 async for result in ws.receive():
@@ -296,6 +312,19 @@ async def streaming_stt_example():
                         text = result['text']
                         is_final = result['is_final']
                         
+                        # Handle word-level timestamps
+                        if 'words' in result and result['words']:
+                            word_timestamps = result['words']
+                            all_word_timestamps.extend(word_timestamps)
+                            
+                            if is_final:
+                                print("Word-level timestamps:")
+                                for word_info in word_timestamps:
+                                    word = word_info['word']
+                                    start = word_info['start']
+                                    end = word_info['end']
+                                    print(f"  '{word}': {start:.2f}s - {end:.2f}s")
+                        
                         if is_final:
                             # Final result - this text won't change
                             full_transcript += text + " "
@@ -311,17 +340,18 @@ async def streaming_stt_example():
             except Exception as e:
                 print(f"Error receiving transcripts: {e}")
             
-            return full_transcript.strip()
+            return full_transcript.strip(), all_word_timestamps
         
         print("Starting streaming STT...")
         
         # Use asyncio.gather to run audio sending and transcript receiving concurrently
-        _, final_transcript = await asyncio.gather(
+        _, (final_transcript, word_timestamps) = await asyncio.gather(
             send_audio(),
             receive_transcripts()
         )
         
         print(f"\nComplete transcript: {final_transcript}")
+        print(f"Total words with timestamps: {len(word_timestamps)}")
         
         # Clean up
         await ws.close()
@@ -336,6 +366,73 @@ if __name__ == "__main__":
     asyncio.run(streaming_stt_example())
 ```
 
+## Batch Speech-to-Text (STT)
+
+For processing pre-recorded audio files, use the batch STT API which supports uploading complete audio files for transcription:
+
+```python
+from cartesia import Cartesia
+import os
+
+client = Cartesia(api_key=os.getenv("CARTESIA_API_KEY"))
+
+# Transcribe an audio file with word-level timestamps
+with open("path/to/audio.wav", "rb") as audio_file:
+    response = client.stt.transcribe(
+        file=audio_file,                    # Audio file to transcribe
+        model="ink-whisper",                # STT model (required)
+        language="en",                      # Language of the audio (optional)
+        timestamp_granularities=["word"],   # Include word-level timestamps (optional)
+        encoding="pcm_s16le",               # Audio encoding (optional)
+        sample_rate=16000,                  # Audio sample rate (optional)
+    )
+
+# Access transcription results
+print(f"Transcribed text: {response.text}")
+print(f"Audio duration: {response.duration:.2f} seconds")
+
+# Process word-level timestamps if requested
+if response.words:
+    print("\nWord-level timestamps:")
+    for word_info in response.words:
+        word = word_info.word
+        start = word_info.start
+        end = word_info.end
+        print(f"  '{word}': {start:.2f}s - {end:.2f}s")
+```
+
+### Async Batch STT
+
+```python
+import asyncio
+from cartesia import AsyncCartesia
+import os
+
+async def transcribe_file():
+    client = AsyncCartesia(api_key=os.getenv("CARTESIA_API_KEY"))
+    
+    with open("path/to/audio.wav", "rb") as audio_file:
+        response = await client.stt.transcribe(
+            file=audio_file,
+            model="ink-whisper",
+            language="en",
+            timestamp_granularities=["word"],
+        )
+    
+    print(f"Transcribed text: {response.text}")
+    
+    # Process word timestamps
+    if response.words:
+        for word_info in response.words:
+            print(f"'{word_info.word}': {word_info.start:.2f}s - {word_info.end:.2f}s")
+    
+    await client.close()
+
+asyncio.run(transcribe_file())
+```
+
+> **Note:** Batch STT also supports OpenAI's audio transcriptions format for easy migration from OpenAI Whisper. See our [migration guide](https://docs.cartesia.ai/api-reference/stt/migrate-from-open-ai) for details.
+
 ## Voices
 
 List all available Voices with `client.voices.list`, which returns an iterable that automatically handles pagination:

{cartesia-2.0.5 → cartesia-2.0.7}/pyproject.toml

@@ -3,7 +3,7 @@ name = "cartesia"
 
 [tool.poetry]
 name = "cartesia"
-version = "2.0.5"
+version = "2.0.7"
 description = ""
 readme = "README.md"
 authors = []