Alibaba Cloud Model StudioText-to-speech
qwen-audio-3.1-tts-flash
Low-latency speech synthesis for voice assistants and real-time conversations, with system voices, voice cloning, natural-language instructions and emotion tags.
01 Price
$0.23per 1M tokens
Free tier: 1e+06 tokens on sign-up.
| Plan or mode | Price |
|---|---|
| input | $0.23 per 1M tokens |
| output | $1.87 per 1M tokens |
Singapore (International deployment scope), USD per token (listed per million tokens). Free quota valid 90 days.
Pricing source, checked 2026-11-16
02 Languages 67, 69 with regional variants
03 Features 5 of 8 listed
- Emotion control
- Voice cloning
- Voice designnot listed
- SSML
- Phoneme inputnot listed
- Speed / prosody control
- Style control
- Multi-speakernot listed
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Voices 70 compatible, browse all
-
Abby
Sample unavailable. The provider may have moved it.
female, american / English
Abby_v3.1 -
Andy
Sample unavailable. The provider may have moved it.
male, american / English
Andy_v3.1 -
Annie
Sample unavailable. The provider may have moved it.
female, american / English
Annie_v3.1 -
Ava
Sample unavailable. The provider may have moved it.
female, american / English
Ava_v3.1 -
Beth
Sample unavailable. The provider may have moved it.
female, american / English
Beth_v3.1 -
Betty
Sample unavailable. The provider may have moved it.
female, american / English
Betty_v3.1
05 Get this record
curl https://voicedex.dev/v1/providers/alibaba/models/qwen-audio-3.1-tts-flash
Free, no key needed. Use model id qwen-audio-3.1-tts-flash with Alibaba Cloud Model Studio's own API. API reference.