text-to-speech benchmarks on edge AI hardware
5 published rows. Each table compares only results with the same model-size class and batch size. Search this workload · JSON.
These 5 results are published as real time factor, not throughput, so they are listed as published, lowest (best) first rather than ranked in like-for-like groups.
| Platform | Result | Model · precision | Grade | Source · date |
|---|---|---|---|---|
| Rockchip RK3576 (NPU, single core of 2) | 0.0690 RTF (lower is better) | mms_tts_eng_200 FP16 | C | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
| Rockchip RV1126B (NPU) | 0.0950 RTF (lower is better) | mms_tts_eng_200 FP16 | C | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
| Rockchip RK3588 (NPU, single core of 3) | 0.108 RTF (lower is better) | mms_tts_eng_200 FP16 | C | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
| Rockchip RK3562 (NPU) | 0.138 RTF (lower is better) | mms_tts_eng_200 FP16 | C | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 0.311 RTF (lower is better) | mms_tts_eng_200 FP16 | C | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
How to read these numbers
Every number is labelled. Confidence: A MLPerf closed, audited · B documented third-party method · C community / review · D vendor-published, not independently verified · E estimate. Power basis: measured with the result · spec vendor spec/envelope · power n/a not published.
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.