HiFi DSPs come with a comprehensive software suite

Frameworks for integration and tuning of audio/speech modules

Flexible, structured frameworks for development, debug, and tuning of audio processing pipelines, helping to reduce development time

Name Description License
XAF (Xtensa Audio Framework) Run-time framework for creating and managing audio and speech processing pipeline chains Cadence license
Sound Open Framework Audio DSP firmware infrastructure and drivers BSD/MIT licensed firmware BSD/GPL licensed drivers
Audio Weaver Graphical UI for real-time tuning and debugging of audio and voice algorithms DSP Concepts
TFLM (Tensor Flow Lite Micro) Industry-standard ML framework for neural network inferencing on resource-constrained devices Creative Commons Attribution 4.0 Apache 2.0

Rich set of DSP and neural network libraries

Utilizing these libraries significantly speeds up development

Name Description License
NDSP Lib (Nature DSP Library) Optimized math and signal processing library Cadence license
CMSIS Lib (Math and DSP libraries) Optimized math and signal processing library supporting CMSIS API Cadence license
NN Lib (Neural Network Library) Optimized NN operators used in speech and audio workloads Cadence license
Codecs Audio, speech/voice codecs (note to Web Team: provide link to list) Cadence license and codec-dependent license

Operating Systems

XOS: Real-time single-core and multi-core scheduler from Cadence

Third-party OS support on Tensilica HiFi DSPs.

Vast array of audio and speech codecs

Ready to deploy and HiFi optimized for a wide range of applications and end products

Speech/Voice Codecs

  • AMR Narrowband, AMR Wideband
  • Bluetooth CVSD, Bluetooth mSBC
  • Bluetooth LE LC3
  • G711, G722, G723.1, G726, G.729AB
  • Opus
  • SILK

Audio Codecs

  • AEC Wideband
  • AMR Wideband+ Decoder, Encoder
  • DAB/MP2 Decoder
  • DAB+ Decoder
  • Digital Radio Mondiale (DRM) Decoder
  • DRA Decoder, 7.1 ch
  • FLAC Decoder, 7.1 ch
  • Misc: Sample Rate Converter
  • Ogg Vorbis Decoder
  • SBC Encoder, Decoder
  • RealAudio 8, 9, and 10 Decoder
  • xHEAAC
  • MP3 Decoder, Encoder
  • MPEG-2 Layer 2 Decoder, 5.1 ch
  • AAC-LC, AACPlusV1, AACPlusV2, 2ch, 7.1ch (Decoder, Encoder)
  • MPEG-H Audio Decoder
  • WMA Decoder, Encoder
  • WMA 10 Pro Decoder 2, 7.1 ch
  • WMA 10 Pro Lossless Decoder 2, 7.1 ch


  • Dolby AC-4 Decoder
  • DD AC-3 Decoder, 5.1 ch
  • DD AC-3 Consumer Encoder (DDCE) 2, 5.1 ch
  • DD Compatible Output Encoder 5.1 ch
  • DD Live Encoder
  • DD Plus Consumer Decoder 7.1 ch
  • DD Plus Decoder/Converter 5.1 ch
  • Dolby Mobile 3+
  • Dolby Multistream Decoder (MS10, MS11, MS12)
  • Dolby ProLogic II and IIx Decoder
  • Dolby TrueHD Decoder 7.1 ch
  • Dolby Volume 2, 5.1 ch


  • DTS Broadcast and DMP 5.1 ch
  • DTS Core Decoder 5.1 ch
  • DTS-HD
  • DTS Interactive Encoder
  • DTS M6 Decoder, 5.1 ch
  • DTS Neural Surround
  • DTS Headphone:X

Page Under Construction

The Strongest Partner Ecosystem for Audio, Voice, Sensor Fusion, and IoT

Cadence has the largest partner ecosystem for audio, voice, sensor fusion, and IoT. With these ready-to-be-deployed audio/speech applications available from our long list of partners, HiFi DSP customers can reduce time to market and offer product differentiation



テンシリカのプロセッサは、既製のプロセッサ/DSP IPであれ、特定のアプリケーションに特化したカスタム・ドメイン・プロセッサであれ、機能安全アプリケーションを可能にすることをお約束します。

Learn More




TIE(Tensilica Instruction Extension)


Learn More





Cadence is committed to keeping design teams highly productive with a range of support offerings and processes designed to keep users focused on reducing time to market and achieving silicon success.



Apply Now



Browse Catalog



Access Now

Xtensa Processor Generator (XPG)

Xtensa Processor Generator (XPG)は、Xtensaのテクノロジーの中核となるものです。この特許取得済みのクラウドベースのシステムは、構築しながら正しいプロセッサが得られ、それに関連するすべてのソフトウェア、モデルなどすべてを自動的に作成します。(ログインが必要です)

Launch XPG