Official pyannoteAI Python SDK
Installation
$ pip install pyannoteai-sdk
Then head over to dashboard.pyannote.ai and create an API key.
Speaker diarization
# instantiate client
from pyannoteai.sdk import Client
client = Client("your-api-key")
# upload conversation file
media_url = client.upload('/path/to/conversation.wav')
# submit a diarization job
job_id = client.diarize(media_url)
# retrieve diarization
diarization = client.retrieve(job_id)
# diarization['output']['diarization'] contains diarization output
Use help(client.diarize) to learn about options.
STT orchestration
# submit a diarization job with STT orchestration
job_id = client.diarize(
media_url,
transcription=True,
transcription_config={"model": "parakeet-tdt-0.6b-v3"})
# retrieve speaker-attributed transcription
orchestration = client.retrieve(job_id)
# orchestration['output']['turnLevelTranscription']
# orchestration['output']['wordLevelTranscription']
Speaker identification
# create a voiceprint from a sample of Lex's voice
lex_url = client.upload('/path/to/lex.wav')
job_id = client.voiceprint(lex_url)
lex = client.retrieve(job_id)
# lex['output']['voiceprint'] contains Lex's voiceprint
# create a voiceprint from a sample of Mark's voice
mark_url = client.upload('/path/to/mark.wav')
job_id = client.voiceprint(mark_url)
mark = client.retrieve(job_id)
# mark['output']['voiceprint'] contains Mark's voiceprint
# use those voiceprints to track Lex and Mark in the conversation
voiceprints = {'lex': lex['output']['voiceprint'], 'mark': mark['output']['voiceprint']}
job_id = client.identify('/path/to/conversation.wav', voiceprints)
identification = client.retrieve(job_id)
# identification['output']['identification'] contains identification output
Use help(client.identify) to learn about options.
Metadata
Release files for pyannoteai-sdk 0.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| pyannoteai_sdk-0.4.0.tar.gz | 14.8 kB | Without provenance | Details for pyannoteai_sdk-0.4.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| pyannoteai_sdk-0.4.0-py3-none-any.whl | Python 3 | none | any | Details for pyannoteai_sdk-0.4.0-py3-none-any.whl |
Total release size: 23.7 kB
Release files / pyannoteai_sdk-0.4.0.tar.gz
| Download URL | pyannoteai_sdk-0.4.0.tar.gz |
|---|---|
| Size | 14.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fbdade06eb54347374acf10698b8c9c0bcdb592f8339c90c5a16fa441ea8cf9d
|
|
BLAKE2b-256 checksum How to use checksums |
f6533e3f14c1382cf14e1dfeb958c08282c44ac07e6965803608e1b748a38273
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.9.25 {"installer":{"name":"uv","version":"0.9.25","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / pyannoteai_sdk-0.4.0-py3-none-any.whl
| Download URL | pyannoteai_sdk-0.4.0-py3-none-any.whl |
|---|---|
| Size | 8.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
36a0175978e0427f27843d690eb4d1e8ec839009ea540516d6dfcdce749cd883
|
|
BLAKE2b-256 checksum How to use checksums |
f98d16e62133ff748931e923c2d29a150a710c85283f533a4148adc42addb6a8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.9.25 {"installer":{"name":"uv","version":"0.9.25","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for pyannoteai-sdk 0.4.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.