Skip to main content

Audio sources, speech, tagging, embeddings, and voice activity for AI agents

Project description

kiarina-agi-audio

English | 日本語

PyPI Python License

[!NOTE] What is this? kiarina-agi-audio provides audio sources, speech-to-text, text-to-speech, voice activity detection, speaker change detection, audio tagging, and audio embeddings for AI agents.

Dependencies

Required Dependencies

Package Version License
jaxtyping >=0.3.3 MIT
kiarina-agi-base >=2.7.0 MIT
kiarina-agi-data >=2.7.0 MIT
kiarina-utils-app >=2.4.0 MIT
kiarina-utils-common >=2.8.0 MIT
kiarina-utils-file >=2.3.1 MIT
NumPy >=2.0,<3 BSD-3-Clause
Pydantic >=2.11.7,<3 MIT
pydantic-settings >=2.10.1,<3 MIT
pydantic-settings-manager >=3.2.0 MIT

Optional Dependencies

Package Extras
ai-edge-litert audio-tagging-provider-yamnet
google-genai asr-provider-google
tts-provider-google
imageio-ffmpeg tts-provider-command
tts-provider-google
tts-provider-mock
tts-provider-openai
kiarina-lib-google asr-provider-google
tts-provider-google
kiarina-lib-openai asr-provider-openai
tts-provider-openai
onnxruntime audio-embedding-provider-clap-onnx
audio-embedding-provider-ecapa-tdnn-onnx
scd-provider-pyannote
vad-provider-silero
openai asr-provider-openai
tts-provider-openai
sounddevice audio-source-mic
soundfile audio-source-file
tiktoken tts-provider-openai

The all Extra installs every optional dependency listed above.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kiarina_agi_audio-2.15.0.tar.gz (81.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kiarina_agi_audio-2.15.0-py3-none-any.whl (162.7 kB view details)

Uploaded Python 3

File details

Details for the file kiarina_agi_audio-2.15.0.tar.gz.

File metadata

  • Download URL: kiarina_agi_audio-2.15.0.tar.gz
  • Upload date:
  • Size: 81.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for kiarina_agi_audio-2.15.0.tar.gz
Algorithm Hash digest
SHA256 1352bca6c689acfd1499a7216f7288bc54ace9fa5d6e4ef7c2328dd33c897cd8
MD5 b1d723ea0c750a2a22bbb0bb7c813007
BLAKE2b-256 9702ed8a9fface6360a1ecd68af7414275be2cad33cd6fa6c3ab8fecf6858db9

See more details on using hashes here.

Provenance

The following attestation bundles were made for kiarina_agi_audio-2.15.0.tar.gz:

Publisher: release-pypi.yml on kiarina/kiarina-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file kiarina_agi_audio-2.15.0-py3-none-any.whl.

File metadata

File hashes

Hashes for kiarina_agi_audio-2.15.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3aba9192fbb4e121d5670ebf43576ad6dc70597cedf7705652d2f1d32037eebd
MD5 85941c5c44bd445a682071f03922fd57
BLAKE2b-256 7ebfb85b905da0e94dd4fcfb9d0d25a07e7b92aef1d8b77fec81d73ab1811178

See more details on using hashes here.

Provenance

The following attestation bundles were made for kiarina_agi_audio-2.15.0-py3-none-any.whl:

Publisher: release-pypi.yml on kiarina/kiarina-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page