Skip to navigation
Authors and ModelsAlibaba Cloud

Qwen Audio 3.1 TTS

Qwen Audio 3.1 TTS
Alibaba Cloud · Audio Generation
POST /v1/audio/speech

Real-time speech synthesis with 19 voices, natural-language delivery direction, inline emotion and sound tags, and streaming audio output.

At a glance

FieldValue
Model idqwen-audio-3-1-tts
Model release date2026-09-23
Input modalitiesText
Output modalitiesAudio
Context window-
Weight precision-
Max output tokens60,000
RegionSingapore
Featurestext_to_speech, multilingual, expressive_prosody, emotion_control, voice_tags, low_latency, streaming
Native inferenceNo
NewYes
Supported endpointsPOST /v1/audio/speech, POST /v1/audio/speech:stream
Alternate model idsqwen-audio-3.1-tts, qwen-audio-3.1-tts-flash, alibaba/qwen-audio-3-1-tts

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.46
Outputper 1M generated tokens$3.74

Example request

curl https://api.empiriolabs.ai/v1/audio/speech \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "qwen-audio-3-1-tts", "input": "Hello from EmpirioLabs."}'

Parameters

ParameterTypeRequiredDefaultDescription
inputstringyes-Text to synthesize, up to 10,000 characters per request. These inline tags change the delivery from the point where they appear: [sad], [amazed], [deep and loud shouting], [trembling], [angry], [excited], [sarcastic], [curious], [like dracula], [bored], [tired], [scornful], [shouting], [asmr], [panicked], [mischievously], [empathetic], [whispers], [reluctantly], [crying], [serious], [very slowly], [very fast]. These add a one-time sound at that point: [gasp], [sighing], [clears throat], [giggles], [laughing], [cough], [snorts]. · Max: 10000
voiceenumno"Emily_v3.1"Voice preset. The 15 English voices read English, and the 4 multilingual voices read Chinese, English, and other languages. Every voice id ends in _v3.1, for example Emily_v3.1. · Allowed: Emily_v3.1, Luna_v3.1, Eric_v3.1, Luca_v3.1, Abby_v3.1, Annie_v3.1, Ava_v3.1, Beth_v3.1, Betty_v3.1, Cally_v3.1, Cindy_v3.1, Donna_v3.1, Andy_v3.1, Brian_v3.1, David_v3.1, longanhuan_v3.1, longanlingxin_v3.1, longanfengyue_v3.1, xunanchuan_v3.1
response_formatenumno"mp3"Audio container. mp3 and opus are compressed, wav is uncompressed PCM in a RIFF header, and pcm is headerless raw samples for chunked playback. · Allowed: mp3, wav, pcm, opus
sample_rateenumno24000Output sample rate in Hz. 24000 suits speech playback, and 48000 gives broadcast-quality output at a larger file size. · Allowed: 8000, 12000, 16000, 22050, 24000, 44100, 48000
speednumberno1Speaking rate multiplier. 0.5 is half speed and 2.0 is double speed. · Range: 0.5 – 2.0
pitchnumberno1Pitch multiplier. Values below 1.0 lower the voice and values above raise it. Pitch also shifts the pace of the rendered audio, so pair it with speed when you want to keep the original duration. · Range: 0.5 – 2.0
volumeintegerno50Output loudness, where 50 is the reference level. · Range: 0 – 100
instructionstringno-Natural-language direction for delivery, up to 1,000 characters. Controls emotion, tone, character, pace, and speaking style, for example ‘Speak quickly in an excited, upbeat tone’ or ‘Read slowly like a late-night radio host’. · Max: 1000
language_hintsarrayno-Language codes that bias pronunciation for mixed-language text, for example [“zh”, “en”]. Leave unset to let the model detect the language. · Allowed: zh, en, fr, de, ja, ko, ru, pt, th, id, vi, es, it, ms, fil, ar
seedintegerno0Sampling seed. Reuse a seed with identical input and settings for a repeatable render. · Range: 0 – 65535
bit_rateintegerno32000Encoder bitrate in bps. Applies to the opus format only, and is ignored for mp3, wav, and pcm. · Range: 6000 – 510000
pronunciationobjectno-Pronunciation overrides keyed by the written form, for example {“重要”: “zhong4 yao4”}. Use it to fix names, acronyms, and homographs.
replaceobjectno-Literal text substitutions applied before synthesis, for example {“EmpirioLabs”: “Empirio Labs”}. Useful for brand names and abbreviations.
enable_markdown_filterbooleannofalseStrip Markdown syntax such as asterisks and underscores before synthesis so formatting characters are not read aloud.

Notes

Voices

  • 19 voices: 15 English voices and 4 multilingual voices. Emily, Luna, Eric, and Luca have British accents. Abby, Annie, Ava, Beth, Betty, Cally, Cindy, Donna, Andy, Brian, and David have American accents. The multilingual voices longanhuan_v3.1, longanlingxin_v3.1, longanfengyue_v3.1, and xunanchuan_v3.1 read Chinese, English, and other languages.
  • Every voice id ends in _v3.1, for example Emily_v3.1.

Delivery direction

  • instruction sets emotion, tone, character, pace, and speaking style in natural language, up to 1,000 characters.
  • Inline tags inside the text change the delivery from that point, for example [excited] or [whispers], or add a one-time sound such as [laughing] or [sighing]. The full list of tags is on the input parameter.
  • SSML input is not supported.

Input limits

  • Up to 10,000 characters per request.
  • language_hints biases pronunciation for mixed-language text.

Output

  • MP3, WAV, PCM, or Opus at 8,000 to 48,000 Hz.
  • POST /v1/audio/speech:stream sends audio chunks while the speech is generated.

Billing

  • Input tokens are the text, and output tokens are the generated audio at 12.5 tokens per second.
  • Speed and pitch change the length of the rendered audio but not the billed tokens. An instruction that slows the delivery adds output tokens.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen-audio-3-1-tts.