Qwen Alibaba Cloud: Qwen3-ASR-1.7B

Name: Qwen3-ASR-1.7B
Author: Qwen Alibaba Cloud

qwen/qwen3-asr-1-7b

activo stt 1 proveedor

Playground

Qwen's 1.7B open-weight multilingual speech recognition model, transcribing pre-recorded audio with word and segment timestamps and optional speaker diarization, and also streaming over an OpenAI-Realtime-shaped WebSocket.

AutorQwen Alibaba Cloud

Idiomas18 idiomas

Modelos variantes3 IDs

Estadoactivo

Inicio rápido

Qwen3-ASR-1.7B

Crea una clave API

Regístrate en AllModels, crea una clave API y guárdala como ALLMODELS_API_KEY.

Crear clave API

Haz una solicitud

Elige un SDK, un modo de solicitud y un lenguaje. El modelo y la ruta del proveedor ya están completados.

STT en streaming con el ElevenLabs SDK

Transmite audio del micrófono o de un archivo a través de la ruta de AllModels compatible con ElevenLabs.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "qwen/qwen3-asr-1-7b",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "sprag"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.

Pasa parámetros del proveedor

Pasa las preferencias de provider mediante las opciones de solicitud del SDK compatible cuando quieras fijar una ruta a un proveedor.

{
  queryParams: {
    provider: {
      only: ["sprag"]
    }
  }
}

Modelos variantes

Son IDs de modelo nativos que el autor o proveedor acepta para la misma familia de modelos canónica.

Qwen3-ASR-1.7B Default

Open-weight checkpoint id published by the Qwen team, which hosting providers rename (Sprag serves it as `rhythm`).

Qwen3-ASR-1.7B

Qwen3-ASR-1.7B (transformers build) Variant

Hugging Face transformers-compatible build of the same weights.

Qwen3-ASR-1.7B-hf

Rhythm (Sprag) Alias

Sprag's product id for this checkpoint, and the only value its transcriptions endpoint accepts for `model`.

rhythm

Proveedores

Distintos proveedores pueden alojar el mismo modelo. Elige un proveedor cuando necesites un backend fijo, o deja que el enrutamiento elija entre ellos.

ProveedorSlugPor horaLatenciaiModosDisponibilidad

Sprag AI 14 parámetros

sprag

$0,075

—

Síncrono · Streaming

Sprag AI

14 parámetros de proveedor documentados para esta ruta.

Precios

ModoIdiomaPor hora

Transcription Cualquiera $0,075

Parámetros

file body · string · obligatorio

Audio to transcribe. Containers: aiff, aac, wav, flac, m4a, webm, mp3, ogg.

model body · string · obligatorio

1 valor enum

Valores

rhythm

frequency_penalty body · number | null · opcional

mín. -2máx. 2

language body · string | null · opcional

ISO-639 tag, not a language name. ENUM ADDED FROM A LIVE PROBE 2026-09-05: Sprag's own spec leaves this a free string and the model card claims 30 languages plus 22 Chinese dialects, but the API rejects th, hi, pl, cs, fil, el, hu, ro, fa, da, fi, sv, mk and sw with HTTP 400, code `unsupported_language`, and a message enumerating exactly these 18. Thirteen of those rejected codes (all but `sw`, which Sprag never documented) are ones the model card claims. Omit the field to have the language detected.

19 valores enum

Valores

enzhkojaderuitfresptmsnlidtrviyuearur

num_speakers body · integer | null · opcional

Hints the speaker count to the diarizer. Ignored without speaker_labels.

presence_penalty body · number | null · opcional

mín. -2máx. 2

prompt body · string | null · opcional

Context prompt. Accepted (200, probe-verified); effect unmeasured.

repetition_penalty body · number | null · opcional

mín. 0máx. 2

response_format body · string | null · opcional

predeterminado "json"6 valores enum

Valores

jsonverbose_jsontextsrtvtt

speaker_labels body · boolean · opcional

Adds a 0-indexed integer `speaker` to each attributed word. Requires response_format=verbose_json (400 otherwise) and `word` in any granularity list sent.

predeterminado false

temperature body · number | null · opcional

mín. 0máx. 2

timestamp_granularities[] body · array | null · opcional

Optional. A verbose response carries both arrays without it; a list that omits `word` silently drops the words array and still returns 200.

top_k body · integer | null · opcional

mín. 0

top_p body · number | null · opcional

mín. 0máx. 1

Idiomas admitidos

18 idiomas

English en

Chinese zh

Yue Chinese (Cantonese) yue

Japanese ja

Korean ko

German de

French fr

Spanish es

Portuguese pt

Italian it

Russian ru

Dutch nl

Arabic ar

Turkish tr

Indonesian id

Malay (macrolanguage) ms

Vietnamese vi

Urdu ur

Funciones

Speech to text

Transcribes pre-recorded audio through an OpenAI /v1/audio/transcriptions shape on the seeded host.

speech_to_text

Realtime streaming transcription

OpenAI-Realtime-shaped WebSocket carrying base64 PCM16 audio inside JSON text frames and returning incremental transcription deltas.

streaming

Word timestamps

response_format=verbose_json returns words[] with float start and end seconds plus segments[], neither of which the realtime path carries.

word_timestamps

Speaker diarization

speaker_labels=true adds a per-request 0-indexed integer speaker to each attributed word, and requires response_format=verbose_json.

diarization

Caption output formats

response_format accepts json, verbose_json, text, srt and vtt.

caption_formats

Context prompt

A `prompt` form field is accepted for recognition context.

context_prompt

Código

STT en streaming con el ElevenLabs SDK

Transmite audio del micrófono o de un archivo a través de la ruta de AllModels compatible con ElevenLabs.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "qwen/qwen3-asr-1-7b",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "sprag"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.