免费AI 免费AI 对文本的语音

将音频和视频发送到100+语言文本上。 10+ AI 模式, 语音探测, 不需要注册 。

9.2K
转录
233.2K
转录的分钟
100+
语言
70+
空闲工具

使用公开的音频和视频工作。 DRM 保护的内容不支持 。

增强的升级
Private transcript
与笔录聊天
以 Pro 解锁 →
在此拖放文件或单击以浏览文件
MP3、WAV、M4A、FLAC、MP4、MKV、MOV、WebM-至多2GB
增强的升级
Private transcript
与笔录聊天
以 Pro 解锁 →
增强的升级
录音: 0:00
实时 伏( 即时)
增强 耳语( 准确)
公共链接:24小时,仅文本 · 签名 7d+音频 · 职业 用于私人链接的私人链接

文本的实时演讲。 AI 自动校正, 使用较长的演讲, 准确性会提高 。

先测试一下麦克风
❤️ 爱你的STT. AI 告诉你的朋友!
你用的是免费的抄本

免费报名每月获得600分钟,或升级无限制的抄本。

每天10分钟免费 600分钟免费,有注册 无信用卡 已加密
免费签名 →
客户端加密存储 — 你的笔录在浏览器里加密了 连我们都看不懂 学习如何运作 →

得到全世界专业人员的信赖

STT.ai 如何运作

三步,准确转录

1. 上传、记录或粘贴 URL

拖放任何音频或视频文件( MP3、 WAV、 MP4 和 20+ 格式) 。 实时记录您的麦克风。 或者粘贴来自YouTube、 Vimeo、 TikTok 和 1300+ 平台的链接 。

2. AI 与你选择模式的连接

从 10 + AI 模型中选择, 包括 Whiseper 、 NVIDIA 加那利( # 1 精度) 和 Moonshine 。 从 100 + 选项中自动检测语言 。 演讲人 diarization 确定谁说了什么 。

3. 出口、份额或一体化

下载为 TXT、 SRT、 VTT、 DOCX、 JSON、 或 PDF 。 通过链接共享 。 使用我们的 API 将抄录入您的应用程序 。 适合字幕、 会议笔记、 播客等等 。

100+
语文支助
70+
空闲工具
1,300+
支持平台
7
导出格式

开发者- 第一 API

将语音到文字整合到您的应用程序中, 以分钟为分钟。 实时 WebSocket 流动的更新 API 。

REST + Web 套件 — 文件上传和实时流
多种模式 — 耳语、加那利语、扩音和更多
议长对角 — 自动检测谁说了什么
弹性产出 — Jsson, TXT, SRT, VTT 配字数时间戳
import requests

response = requests.post(
    "https://api.stt.ai/v1/transcribe",
    headers={"Authorization": f"Bearer {API_KEY}"},
    files={"file": open("meeting.mp3", "rb")},
    data={
        "model": "large-v3-turbo",
        "language": "auto",
        "diarize": "true",
        "response_format": "json",
    },
)

result = response.json()
for seg in result["segments"]:
    print(f"{seg['speaker']}: {seg['text']}")

准备好抄写了吗?

免费上传第一个文件 没有信用卡,没有注册 每月600分钟的自由计划

开始切换

常见问题

speech to text runs in your browser: paste a URL, upload a file, or record from your mic. STT.ai picks the AI model and returns the transcript in under 5 minutes. Export as TXT, SRT, VTT, DOCX, JSON, or PDF.

Yes — every visitor gets 600 free minutes/month on STT.ai, usable for speech to text the same as any other workflow. Paid plans starting at $5/month unlock longer files, private transcripts, and priority queueing.

speech to text runs on the same AI models as the rest of STT.ai — our best models reach 95-97% accuracy on clean speech (3-5% Word Error Rate on benchmarks). Switch models on the fly if the first pass is below your target.

speech to text can run on any of STT.ai's 10+ models — STT.ai Enhanced (most accurate), Whisper Large V3 (99 languages), NVIDIA Canary (#1 WER on supported langs), Whisper Turbo (fast), Moonshine (lightweight), and more.

Yes. Every transcript exports as SRT or VTT — works with YouTube, Vimeo, TikTok, VLC, and every major video player. The burn-subtitles tool overlays them onto video as hardsubs.

Yes. Speaker diarization automatically labels each voice (Speaker 1, Speaker 2, ...) and you can rename them in the built-in editor. Works across all models and languages.

Most speech to text jobs finish in under 5 minutes. A 1-hour audio file typically completes in 2-3 minutes with our fastest models. Speed depends on chosen model and current GPU load.

speech to text accepts 20+ formats — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, and more. Output to TXT, SRT, VTT, DOCX, JSON, or PDF.

Yes. Audio files submitted to speech to text are processed and deleted by default. Pro plans add client-side encryption — even if STT.ai's database is breached, your transcripts are unreadable without your key. Data is never used for model training without explicit opt-in.

Yes. STT.ai offers a REST API with Python and Node.js SDKs, plus an MCP server for Claude and Cursor — all usable for speech to text workflows. Free API tier includes 100 minutes/month.

Yes. Every transcript opens in the built-in editor where you can correct words, rename speakers, adjust timestamps, and add notes. All changes save automatically.

Every transcript gets a unique shareable URL. Export to DOCX or PDF for email. Pro plans add password-protected and permanent links — useful for client work.

STT.ai handles 1,300+ platforms including YouTube, Vimeo, TikTok, SoundCloud, Zoom, Google Meet, podcast hosts, and more. URL transcription works with publicly-available content only — DRM-protected sources can't be transcribed.