Cadence announces new Tensilica HiFi iQ DSP Next-gen Voice AI and audio in the home or car. Cadence Tensilica is a leader in customizable processor IP (Intellectual Property) cores designed to be highly specialized for specific tasks, such as audio processing, computer vision, or AI acceleration.
Today, the company announced the Cadence Tensilica HiFi iQ DSP IP, the sixth generation of its highly successful HiFi DSP family, based on a new architecture purpose-built for next-generation voice AI and emerging immersive audio. I had a chance to catch up with Amol Borkar, Group Director of Product Management and Marketing for Tensilica DSPs, and learn about this new line of products ready for the future DSP needs of audio.
Big ecosystem
Tensilica HiFi DSPs for audio, voice, and speech applications gather 160+ licensees and more than 200 ecosystem partners who ship more than 1.5 billion HiFi DSPs annually. The number one DSP in the market is also used in more than 300 audio software packages.
Major trends in Audio
Multiple industry executives mentioned that voice is the new keyboard. One could say that voice is the new UI (User Interface). With the help of voice, it is easy to dictate to your device and get highly accurate input. Success is driven by small language models and language models that target Voice AI-driven applications.
A key application is the immersive experience in cars where hands are usually busy driving. This enables an immersive in-car experience ready for the vehicles of the near future. Some of the use-case scenarios include spatial and 3D audio, immersive audio playback, sound bubbles and zoning, support for advanced codecs, audio alerts, ADAS warnings, and high-quality voice processing.
One big trend in current and future cars is how to make the cabin quieter, and Cadence Tensilica HiFi iQ has a compelling solution for that too. Cars today have up to 16 speakers and 12-channel Dolby Atmos @ 48kHz, while the future is expected to have 30 speakers for immersive audio decoding at 96kHz and AI-enhanced channel rendering optimization.
The audio workload of the car of the future will double compared to today. The number of microphones is expected to double from four to eight, and again, with enhanced AI, the workload is expected to grow by 2x to 3x. The mic array is expected to expand from the front to the rear row, with the voice interface enhanced by small-model AI. This workload is expected to increase by 2x to even 8x.
Sixth-generation HiFi DSP
HiFi iQ The sixth-generation HiFi DSP, HiFi iQ, delivers greater performance and energy efficiency for voice-based AI applications and the latest immersive audio formats. As these applications proliferate in the home entertainment, automotive infotainment, and smartphone markets, the HiFi iQ DSP delivers the performance and energy efficiency required to meet growing SoC computational demands.
Compared to the industry-leading Tensilica HiFi 5s DSP, the HiFi iQ DSP offers 2x greater compute performance, 8x higher AI performance, and more than 25% energy savings for most workloads, delivering over a 40% performance uplift on numerous audio codecs.
With the increased growth of AI across virtually every facet of the industry, audio and language have become critical interfaces for users,” said Anshel Sag, VP and principal analyst, Moor Insights and Strategy. “The AI performance and energy savings with Cadence’s new flagship Tensilica HiFi iQ DSP position it to enable future AI-enhanced applications and offload processing from other IPs.
Available in Q2 26
Tensilica HiFi iQ DSP features a new architecture that was necessary to enable this quantum leap in performance. It is purpose-built for next-generation voice AI and audio formats. With 8x faster AI performance enabled by more MACs, the DSP brings 2x raw performance due to the wider SIMD and a 40+ percent improvement on codecs. There is native support for FP8 and FP16 model formats to run cutting-edge voice AI models and an overall 25 percent energy savings. The new HiFi iQ fits into a very rich software ecosystem enabling faster time to market.
A number of factors are driving the need for greater computation, including the need for richer experiences enabled by the latest immersive audio codecs, audio processing at higher sampling rates, object-based rendering, seamless natural language processing (NLP), and automotive road-noise cancellation (RNC). These use cases require increased AI/ML capabilities and enhanced audio/voice pre- and post-processing functions, which demand more computations performed with low latency and low power for on-device processing in edge AI and physical AI applications. Since most of these designs are power-constrained, increasing the core’s operating frequency or integrating multiple cores is often not a viable option.
The Tensilica HiFi iQ DSP’s architectural enhancements and increased computational capability enable sophisticated immersive audio codecs such as Dolby MS12, Eclipsa Audio, Opus HD, Audio Vivid, and others to run with higher efficiency than on previous HiFi DSPs. These advancements resulted in more than 40% greater performance than the Tensilica HiFi 5s DSP on multiple codecs. Signal processing algorithms for keyword spotting (KWS), active noise cancellation (ANC), beamforming, and automatic speech recognition (ASR) can be performed seamlessly, enabling state-of-the-art NLP functions. Additionally, multi-stream and multi-channel audio playback facilitates the rendering of 3D spatial zones and sound bubbles, delivering highly realistic listening experiences.
With recent advancements in LLMs, SLMs, energy-efficient SoCs, and on-device AI, voice input is poised to become the new keyboard. To enable seamless interaction with the latest physical AI applications, SoC providers need energy-efficient and easily programmable IP capable of running SLMs on-device while performing voice and audio processing seamlessly,” said Boyd Phelps, senior vice president and general manager of the Silicon Solutions Group at Cadence. “As the market leader in DSPs for audio, voice, speech, and AI applications with billions of Tensilica HiFi DSPs in a wide array of embedded products, SoC and system vendors rely on Cadence to continue to push the envelope for performance and energy efficiency.
The Tensilica HiFi iQ DSP is fully capable of running popular small language models (SLMs) and large language models (LLMs) on the DSP itself, acting as an all-in-one AI processor for voice AI applications. For an additional performance boost, it can be easily paired with Cadence’s Neo NPUs or customer-built NPUs to further maximize performance and energy efficiency.
The Tensilica HiFi iQ DSP is compatible with the Cadence NeuroWeave Software Development Kit (SDK), TensorFlow Lite for Micro (TFLM), LiteRT, and ExecuTorch environments for AI model execution. The Tensilica HiFi iQ DSP also leverages the vast ecosystem of partners and OEMs that have developed software libraries, compilers, codec packages, frameworks, and more to enable easy deployment and fast time to market.
Availability and Related Resources
The Tensilica HiFi iQ DSP will be available to lead customers and partners in the first quarter of 2026, with general availability expected in the following quarter. The HiFi iQ DSP is also targeted for ISO 26262 functional safety (FuSa) certification, making it suitable for safety-critical applications. Future HiFi iQ DSP support for cache-coherent multicore configurations is planned.
