Official documentation
esp-sr speech recognition components: README (version 2.6.0)
Espressif Systems, Espressif Systems, ESP Component Registry, 2026
Read the originalRead on October 17, 2026
- What it is
- The README of Espressif's esp-sr component for its ESP32 chips. It lists the offline speech command model MultiNet, the wake word engine and the supported chip targets.
- How much weight it carries
- Official documentation from the chip maker, versioned. Limits are stated by the vendor, and an earlier overview page gave a lower command count, so check the version you use.
Facts taken from this source
- Espressif says its MultiNet model recognizes up to 300 Chinese or English speech commands, and that developers can add commands without training the model again.
“supports up to 300 Chinese or English speech commands” (Speech Command Word Recognition MultiNet section)
- Espressif's esp-sr README lists the ESP32-S3, ESP32-P4 and ESP32-S31 as the supported targets for its MultiNet speech command recognition, and does not list the original ESP32.
“Speech Command Recognition | Supported Targets | ESP32-S3 | ESP32-P4 | ESP32-S31” (Speech Command Recognition)
- Espressif says that from ESP-SR v2.6.0, its WakeNet10s wake word model can run on chips without SIMD instructions, including the original ESP32.
“we support WakeNet10s, which can run on chips without PIE (SIMD) instructions, such as ESP32” (News (2026/10/09))
- Espressif says its WakeNet9s wake word model can run on chips that have no PSRAM and no SIMD support, such as the ESP32-C3 and ESP32-C5.
“We add a new model WakeNet9s, which can run on chips that do not have PSRAM and do not support SIMD” (News (2025/04/21))