Picovoice Orca - Text-to-Speech Latency Benchmark

Prerequisites

• Ubuntu 20.04 (x86_64)
• Git
• Python 3.8+
• Picovoice Console Account

Usage

1. Clone the repository:

git clone https://github.com/Picovoice/tts-latency-benchmark.git

2. Install the dependencies:

pip3 install -r requirements.txt

3. Download the picoLLM model

For each benchmark a picoLLM model is required to generate responses from the LLM. The picoLLM model used in the benchmark is llama-3.2-1b-instruct-385 and can be downloaded from Picovoice Console.

4. Run the benchmark:

python3 benchmark.py \
--picovoice-access-key ${PV_ACCESS_KEY} \
--picollm-model-path ${PICOLLM_MODEL_PATH} \
--engine picovoice_orca \

Replace ${PICOLLM_MODEL_PATH} with the path to the model you downloaded. Replace ${PV_ACCESS_KEY} with your AccessKey obtained from Picovoice Console. Everyone who signs up for Picovoice Console receives a unique AccessKey.