MOSS-Transcribe-Diarize-Pro
RecommendedSpeech recognitionMOSS-Transcribe-Diarize-Pro outputs high-accuracy transcripts together with speaker identities and timestamps, built for multi-speaker scenarios such as meetings, interviews, podcasts, and film or TV content.
ENDPOINT
POST /v1/audio/transcriptions
Current request path
Input
Audio
Content accepted by the request
Output
Text
Content returned on success
Model overview
A multi-speaker transcription model supporting audio up to 60 minutes long. Use the stable model ID moss-transcribe-diarize-pro by default; to reproduce a fixed version, pass moss-transcribe-diarize-pro-2026-07-03 in model.
Billing
Billing methodCNY price 40% OFFActual deduction 40% OFF
By input audio or video duration4024 credits / hour
CNY 2CNY 1.20 / hourEach request is billed by actual usage. CNY prices are for reference; the final charge follows the credits bill. View full pricing
Modality support
TTextOutput only
AAudioInput only
IImageNot supported
VVideoNot supported
Supported endpoints
Chat Completions
/v1/chat/completionsNot supportedResponses
/v1/responsesNot supportedMessages
/v1/messagesNot supportedCount input tokens
/v1/messages/count_tokensNot supportedSingle-speaker speech
/v1/audio/speechNot supportedMulti-speaker dialogue speech
/v1/audio/speech/speakersNot supportedAudio transcription
/v1/audio/transcriptionsSupportedVoice design
/v1/audio/voice/generationsNot supportedRealtime interaction
/v1/realtimeNot supportedImage generation
/v1/images/generationsNot supportedCapabilities
PerformanceHigh
Inference speedMedium
Streaming Supported
Async task API Supported
- Supports audio up to 60 minutes
- Extra-long context — 32k
- Up to 16k output length
- Robust handling of noise and overlapping speech
- Keyterm boosting for domain-specific terms, names, brands, and business terminology
Rate limits
LimitCapScope
Requests per minute (RPM)
70 requestsShared across all model endpoints except MOSS-Live-1.0 and Nex-N2.6 for the same userRequests per day (RPD)
30,000 requestsShared across all model endpoints except MOSS-Live-1.0 and Nex-N2.6 for the same userConcurrency
2Each user can process up to 2 transcription tasks at the same time on this model.Versions and snapshots
Model ID
moss-transcribe-diarize-proSnapshot
moss-transcribe-diarize-pro-2026-07-03Latest