Console

Model ListMOSS-Transcribe

MOSS-Transcribe

LatestSpeech recognition

MOSS-Transcribe-1.0 delivers high-accuracy transcription across speakers of different ages and voice characteristics — from children to the elderly. It fits meetings, interviews, podcasts, and film or TV content, producing clear and accurate transcripts even in complex acoustic environments.

View API reference

ENDPOINT

POST /v1/audio/transcriptions

Current request path

Input

Audio

Content accepted by the request

Output

Text

Content returned on success

Model overview

Standard audio transcription model. Use the stable model ID moss-transcribe-1.0 by default; to reproduce a fixed version, pass moss-transcribe-1.0-2026-07-22 in model.

Billing

Billing methodCNY priceActual deduction
By input audio or video durationCNY 0.80 / hour16 credits / hour

Each 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

Single-speaker speech/v1/audio/speechNot supported
Multi-speaker dialogue speech/v1/audio/speech/speakersNot supported
Audio transcription/v1/audio/transcriptionsSupported
Voice design/v1/audio/voice/generationsNot supported
Multimodal understanding/v1/responsesNot supported
Realtime video understanding/v1/realtimeNot supported
Image generation/v1/images/generationsNot supported

Capabilities

PerformanceHigh
Inference speedMedium
Streaming Not supported
Async Supported
  • High-accuracy transcription with high-quality text output
  • Adapts to speakers with different voices, tones, and pronunciation
  • Covers meetings, interviews, podcasts, film, and TV scenarios

Versions and snapshots

Model IDmoss-transcribe-1.0
Snapshotmoss-transcribe-1.0-2026-07-22Latest