Model ListMOSS-TTS-v1.0-Pro

MOSS-TTS-v1.0-Pro

LegacySpeech generation

MOSS-TTS is our latest flagship text-to-speech model. It delivers high-fidelity voice cloning that faithfully reproduces a speaker's identity, tone, and prosody, producing natural, vivid, and expressive speech.

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-1.0-pro by default; to reproduce a fixed version, pass moss-tts-1.0-pro-2026-02-07 in model.

Billing

This page does not include placeholder pricing. Refer to console pricing and bills for actual units and rates.

ItemUnit priceDescription

Model invocationSee pricingUsage is measured from actual requests and outputs. Refer to console bills for the final amount.

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

Capabilities

PerformanceHigh

Inference speedMedium

Streaming Not supported

Async Supported

65,536-token context window
Up to 45,000 output tokens
15+ languages supported
Phoneme-level pronunciation control & token-level duration control

Versions and snapshots

Model IDmoss-tts-1.0-pro

Snapshotmoss-tts-1.0-pro-2026-02-07Latest