Textefun-asr
阿里巴巴 · Texte

Fun-ASR is a multilingual speech recognition model from Alibaba Cloud for long-form audio transcription. It supports major Chinese dialects, regional accents, and 30 languages, with punctuation prediction and text normalization.

Aperçu

Modalités
Publié le22 août 2025

Tarifs

Disponibilité

État du service24 dernières heures

Paramètres

Modèle / versionfun-asr
Modalités d’entréeAudio
Modalités de sortieTexte
Paramètres d’échantillonnage—

Exemple de requête

# Base64-encode your audio file
AUDIO_BASE64=$(base64 < audio.wav | tr -d '\n')

curl "https://api.agtcloud.cn/v1/audio/transcriptions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "fun-asr",
    "input_audio": {
      "data": "'"$AUDIO_BASE64"'",
      "format": "wav"
    }
  }'

Points de terminaison

sttPOST /v1/audio/transcriptionsRéférence API

Transcribes audio into text. Accepts base64-encoded audio input and returns the transcribed text.

EXPLORE MODELS

Plus de Texte

Comparez les capacités, le contexte et le prix des modèles du même type.

Tout parcourir
MiniMax

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. Open weights are planned.

MiniMax

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. Open weights are planned.

DeepSeek

Currently powered by DeepSeek-V4.1-Flash-1017, with native multimodal visual understanding and support for both thinking and non-thinking modes. Suitable for complex reasoning, coding, long-document analysis, visual understanding, and tool calling.

字节跳动

A next-generation omni-modal large model with native unified understanding of text, vision, and audio. It features a 1M-token context window and strong overall multimodal capabilities, with significant improvements in task completion for coding and agentic scenarios.

字节跳动

Seed-Evolving is a model in the Seed series designed for agentic workflows, multimodal understanding, and software development. This update further strengthens complex task planning, visual reasoning, tool execution, and result verification, enabling the model to better understand images, videos, and real software environments, and to more reliably complete the full workflow from information gathering to final delivery. Use the unified Model ID **`doubao-seed-evolving`** to continuously access the latest model capabilities without needing to track or switch between model versions.