Console

Model ListMOSS-TTS-v1.5-Flash

MOSS-TTS-v1.5-Flash

RecommendedSpeech generation

MOSS-TTS-v1.5-Flash is designed for low-latency streaming speech generation. It provides high-fidelity voice cloning and speech control while continuously returning audio chunks with stream=true.

View API reference

ENDPOINT

POST /v1/audio/speech

Current request path

Input

Text + voice_id

Content accepted by the request

Output

Audio

Content returned on success

Model overview

Single-speaker text-to-speech model. Use the stable model ID moss-tts-1.5-flash by default; to reproduce a fixed version, pass moss-tts-1.5-flash-2026-06-26 in model.

Billing

Billing methodCNY priceActual deduction
By input charactersCNY 2.00 / 10K characters40 credits / 10K characters

Each request is billed by actual usage. CNY prices are for reference; the final charge follows the credits bill. View full pricing

Modality support

TTextInput only
AAudioOutput only
IImageNot supported
VVideoNot supported

Supported endpoints

Single-speaker speech/v1/audio/speechSupported
Multi-speaker dialogue speech/v1/audio/speech/speakersNot supported
Audio transcription/v1/audio/transcriptionsNot supported
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

PerformanceHigher
Inference speedMedium
Streaming Supported
Async Supported
  • 32,768-token context window
  • Up to 7,500 output tokens
  • Cantonese supported
  • 30+ languages supported
  • Phoneme-level pronunciation control & token-level duration control

Versions and snapshots

Model IDmoss-tts-1.5-flash
Snapshotmoss-tts-1.5-flash-2026-06-26Streaming version