Unisound · Rate Limits
Unisound Rate Limits
Unisound Token Hub enforces per-model RPM (requests per minute) and TPM (tokens per minute, input + output combined) limits; the API refuses further requests when a threshold is exceeded within the window. No rate-limit response headers are documented. On the legacy AI Open Platform, error code 20206 signals concurrency limit exceeded and 20207 quota exhausted.
Unisound Rate Limits is the machine-readable rate-limit profile for Unisound on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 9 rate-limit definitions, measuring requests_per_minute and tokens_per_minute.
Tagged areas include Rate Limiting and Artificial Intelligence.
9 Limits
Rate LimitingArtificial Intelligence
Limits
Text models (u2, u2-med, kimi-k3, glm-5.2) requests model
100
Text models (u2, u2-med, kimi-k3, glm-5.2) tokens model
10000000
Async speech transcription tasks (v1_audio_asr_tasks, u2-asr) interface
20
Async speech synthesis tasks (v1_audio_speech_tasks, u2-tts / u2-tts-clone) interface
20
Voice clone (v1_audio_voices_clone, u2-tts-clone) interface
20
Document parsing tasks (v1_files_parser_tasks, u1-ocr) requests interface
20
Document parsing tasks (v1_files_parser_tasks, u1-ocr) tokens interface
100000
OCR image extraction (v1_ocr_image_extract, u1-ocr / u1-ocr-med) requests interface
20
OCR image extraction (v1_ocr_image_extract, u1-ocr / u1-ocr-med) tokens interface
100000