Alibaba Cloud Model StudioSpeech-to-speech
qwen-audio-3.0-realtime-flash
End-to-end full-duplex real-time voice conversation model with function calling and web search (cost-optimized tier).
01 Price
$0.23per 1M tokens
| Plan or mode | Price |
|---|---|
| input: text | $0.23 per 1M tokens |
| input: audio | $0.93 per 1M tokens |
| output: text | $0.70 per 1M tokens |
| output: audio | $1.87 per 1M tokens |
Singapore (International), USD per token (listed per million tokens); audio tokens = seconds x 12.5; with text+audio output only audio is billed.
Pricing source, checked 2026-11-16
02 Languages 13
03 Features 0 of 19 listed
- Word timestampsnot listed
- Speaker diarizationnot listed
- Punctuationnot listed
- Profanity filternot listed
- Custom vocabularynot listed
- Language detectionnot listed
- Translationnot listed
- Sentimentnot listed
- PII redactionnot listed
- Summarizationnot listed
- Topic detectionnot listed
- Emotion controlnot listed
- Voice cloningnot listed
- Voice designnot listed
- SSMLnot listed
- Phoneme inputnot listed
- Speed / prosody controlnot listed
- Style controlnot listed
- Multi-speakernot listed
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Voices 5 compatible, browse all
-
Long An Ling Xi
Cute and sweet
Sample unavailable. The provider may have moved it.
female, 25 / Chinese +1
longanlingxi -
Long An Ling Xin
Warm and empathetic
Sample unavailable. The provider may have moved it.
female, 25 / Chinese +1
Social companionship (flagship voice)longanlingxin -
Long An Lu Feng
Bright and cheerful
Sample unavailable. The provider may have moved it.
male, 25 / Chinese +1
longanlufeng -
Long An Xiao Xin
Friendly and lively
Sample unavailable. The provider may have moved it.
female, 22 / Chinese +1
longanxiaoxin -
No sample published
longanqian
Sample unavailable. The provider may have moved it.
language not listed
longanqian
05 Get this record
curl https://voicedex.dev/v1/providers/alibaba/models/qwen-audio-3.0-realtime-flash
Free, no key needed. Use model id qwen-audio-3.0-realtime-flash with Alibaba Cloud Model Studio's own API. API reference.