alibaba/qwen-audio-3.0-tts-flash

qwen-audio-3.0-tts-flash
Docs
Schema

[Core Function] Qwen-Audio 3.0 TTS Flash is Alibaba's low-latency Qwen-Audio text-to-speech model on the same SpeechSynthesizer endpoint family as CosyVoice. [Strengths] Fast synthesis with voice, format, sample-rate, prosody, SSML, instruction, language_hint, and AIGC watermark controls; system voices include longanhuan_v3.6, longjielidou_v3.6, loongeva_v3.6, and loongjohn (see the Qwen-Audio-TTS voice list). [Best For] Voice assistants, interactive prompts, short announcements, multilingual product flows, and latency-sensitive batch TTS using Qwen-Audio voices. [Limitations] Does not expose hot_fix or Markdown filtering. Do NOT mix Plus-only voices (e.g. longanlingxin) with Flash. Use Plus when maximum narration quality matters more than turnaround time. [Routing] Choose Flash when speed matters most. Choose qwen-audio-3.0-tts-plus for premium narration quality.

$9.4702/M chars
text-to-speech

Input

Text to synthesize. Required. Max 20,000 Unicode characters. Supports plain text and SSML (set enable_ssml to true) per Alibaba documentation.
Voice ID for qwen-audio-3.0-tts-flash only. Use a Flash system voice (e.g. longanhuan_v3.6, longjielidou_v3.6, loongeva_v3.6, loongjohn) or a Flash base/cloned voice ID from the official Qwen-Audio-TTS voice list: https://help.aliyun.com/zh/model-studio/qwen-audio-tts-voice-list . Do not mix Plus system voices with Flash.
AIGC PropagateID. Only effective when enable_aigc_tag is true.
AIGC ContentPropagator. Only effective when enable_aigc_tag is true.
Optional speaking-style instruction. Enforced weighted length ≤100 (CJK ideographs / Han count as 2; other characters count as 1).
Audio bit rate in kbps. Optional. Range 6 to 510. Only supported when format is opus; do not use for mp3, pcm, or wav.
Embed AIGC invisible watermark into wav/mp3/opus output. Supported on Qwen-Audio 3.0 TTS Plus and Flash.
Whether to parse text as SSML. Default false. When true, text must follow Alibaba SpeechSynthesizer SSML rules.
Audio encoding format. Default mp3.
mp3
Target language hint for pronunciation (numbers, symbols, minor languages).
language_hint
Pitch multiplier. Default 1.0. Range 0.5 (lower) to 2.0 (higher).
Speech rate multiplier. Default 1.0. Range 0.5 (slow) to 2.0 (fast).
Audio sample rate in Hz. Default 22050.
22050
Random seed for reproducible synthesis when text, voice, and other parameters are identical. Default 0. Range 0 to 65535.
Output volume. Default 50. Range 0 (silent) to 100 (maximum).

Result

No results yet

Run the model to preview the output here.

Next:

README

Attributes

Series

Parameters

Name Description Type Required Enums
text Text to synthesize. Required. Max 20,000 Unicode characters. Supports plain text and SSML (set enable_ssml to true) per Alibaba documentation. string Yes -
voice Voice ID for qwen-audio-3.0-tts-flash only. Use a Flash system voice (e.g. longanhuan_v3.6, longjielidou_v3.6, loongeva_v3.6, loongjohn) or a Flash base/cloned voice ID from the official Qwen-Audio-TTS voice list: https://help.aliyun.com/zh/model-studio/qwen-audio-tts-voice-list . Do not mix Plus system voices with Flash. string Yes -
aigc_propagate_id AIGC PropagateID. Only effective when enable_aigc_tag is true. string No -
aigc_propagator AIGC ContentPropagator. Only effective when enable_aigc_tag is true. string No -
instruction Optional speaking-style instruction. Enforced weighted length ≤100 (CJK ideographs / Han count as 2; other characters count as 1). string No -
bit_rate Audio bit rate in kbps. Optional. Range 6 to 510. Only supported when format is opus; do not use for mp3, pcm, or wav. integer No -
enable_aigc_tag Embed AIGC invisible watermark into wav/mp3/opus output. Supported on Qwen-Audio 3.0 TTS Plus and Flash. boolean No true, false
enable_ssml Whether to parse text as SSML. Default false. When true, text must follow Alibaba SpeechSynthesizer SSML rules. boolean No true, false
format Audio encoding format. Default mp3. string No mp3, pcm, wav, opus
language_hint Target language hint for pronunciation (numbers, symbols, minor languages). string No zh, en, fr, de, ja, ko, ru, pt, th, id, vi, es, it, ms, fil, ar
pitch Pitch multiplier. Default 1.0. Range 0.5 (lower) to 2.0 (higher). number No -
rate Speech rate multiplier. Default 1.0. Range 0.5 (slow) to 2.0 (fast). number No -
sample_rate Audio sample rate in Hz. Default 22050. integer No 8000, 16000, 22050, 24000, 44100, 48000
seed Random seed for reproducible synthesis when text, voice, and other parameters are identical. Default 0. Range 0 to 65535. integer No -
volume Output volume. Default 50. Range 0 (silent) to 100 (maximum). integer No -

Pricing

Unit: $/M chars

Pricing
$9.4702/M chars
  • alibaba/qwen-audio-3.0-tts-plus: [Core Function] Qwen-Audio 3.0 TTS Plus is Alibaba’s high-quality Qwen-Audio text-to-speech model on the same SpeechSynthesizer endpoint family as CosyVoice. [Strengths] Natural speech synthesis with voice, format, sample-rate, prosody, SSML, instruction, language_hint, and AIGC watermark controls; system voices include longanlingxin and longanlufeng (see the Qwen-Audio-TTS voice list). [Best For] Premium narration, brand voiceovers, multilingual product audio, and quality-sensitive batch TTS when Qwen-Audio voices are preferred. [Limitations] Does not expose hot_fix or Markdown filtering. Do NOT use for real-time streaming or word-level timestamps. Do NOT mix Flash-only voices (e.g. longanhuan_v3.6) with Plus. [Routing] Choose Plus when speech quality is the priority. Choose qwen-audio-3.0-tts-flash when lower latency matters more.

Related Resources

Qwen Audio
Qwen AudioSeries
alibaba/qwen-audio-3.0-tts-plus
alibaba/qwen-audio-3.0-tts-plustext-to-speech