starters

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deepgram Starter Apps

Deepgram 启动模板应用

Clone a working demo and start building. Every starter is a minimal, runnable app you can extend.

克隆一个可运行的演示项目并开始开发。每个启动模板都是一个极简的可运行应用，您可以在此基础上进行扩展。

1. Pick Your Feature

1. 选择您需要的功能

What do you want to build?

Transcribe a file →
```
transcription
```
— send audio/video, get text back (REST, Nova)
Transcribe a live stream →
```
live-transcription
```
— real-time speech-to-text (WebSocket, Nova)
Generate speech →
```
text-to-speech
```
— send text, get audio back (REST)
Stream speech →
```
live-text-to-speech
```
— real-time text-to-audio (WebSocket)
Analyze text or audio →
```
text-intelligence
```
— sentiment, topics, intents, summaries (REST)
Build a voice agent →
```
voice-agent
```
— conversational AI agent (WebSocket, agent.deepgram.com)
Conversational STT with turn detection →
```
flux
```
— Deepgram Flux for voice agents and interactive assistants (WebSocket,
```
/v2/listen
```
)

Nova vs Flux for speech-to-text: use

transcription

live-transcription

(Nova,

/v1/listen

) for general-purpose transcription, captions, and batch workloads. Use

flux

(Flux,

/v2/listen

) when you need built-in turn detection for conversational audio. See the

api

skill for a full comparison.

您想要构建什么功能？

转录文件 →
```
transcription
```
— 上传音频/视频，获取文本结果（REST、Nova）
实时转录直播流 →
```
live-transcription
```
— 实时语音转文字（WebSocket、Nova）
生成语音 →
```
text-to-speech
```
— 传入文本，获取音频结果（REST）
实时流式语音生成 →
```
live-text-to-speech
```
— 实时文字转音频（WebSocket）
分析文本或音频 →
```
text-intelligence
```
— 情感分析、主题识别、意图识别、文本摘要（REST）
构建语音Agent →
```
voice-agent
```
— 对话式AI Agent（WebSocket、agent.deepgram.com）
带话轮检测的对话式语音转文字 →
```
flux
```
— 适用于语音Agent和交互式助手的Deepgram Flux（WebSocket、
```
/v2/listen
```
）

语音转文字的Nova与Flux对比：通用转录、字幕生成和批量处理场景，使用

transcription

或

live-transcription

（Nova、

/v1/listen

）。当您需要为对话音频提供内置话轮检测时，使用

flux

（Flux、

/v2/listen

）。查看

api

技能获取完整对比信息。

2. Pick Your Stack

2. 选择您的技术栈

Language	Frameworks
JavaScript	`node`
TypeScript	`bun` , `deno`
Python	`fastapi` , `flask` , `django`
Go	`go`
Java	`java`
C#	`csharp`
Rust	`rust`
Ruby	`ruby`
PHP	`php`
C++	`cpp`

编程语言	框架
JavaScript	`node`
TypeScript	`bun` , `deno`
Python	`fastapi` , `flask` , `django`
Go	`go`
Java	`java`
C#	`csharp`
Rust	`rust`
Ruby	`ruby`
PHP	`php`
C++	`cpp`

3. Clone and Run

3. 克隆并运行

Every starter lives at

https://github.com/deepgram-starters/{framework}-{feature}

git clone https://github.com/deepgram-starters/{framework}-{feature}.git
cd {framework}-{feature}

Set your API key and follow the README:

export DEEPGRAM_API_KEY=your_key_here

Get an API key at https://console.deepgram.com.

每个启动模板的仓库地址为

https://github.com/deepgram-starters/{framework}-{feature}

：

git clone https://github.com/deepgram-starters/{framework}-{feature}.git
cd {framework}-{feature}

设置您的API密钥并遵循README中的步骤：

export DEEPGRAM_API_KEY=your_key_here

在 https://console.deepgram.com 获取API密钥。

Examples

示例

"I want to build a voice agent in Python" →

git clone https://github.com/deepgram-starters/fastapi-voice-agent.git

"I need live transcription in my Node app" →

git clone https://github.com/deepgram-starters/node-live-transcription.git

"I want to add text-to-speech to my Go service" →

git clone https://github.com/deepgram-starters/go-text-to-speech.git

"I want to analyze audio for sentiment in C#" →

git clone https://github.com/deepgram-starters/csharp-text-intelligence.git

"我想用Python构建一个语音Agent" →

git clone https://github.com/deepgram-starters/fastapi-voice-agent.git

"我需要在Node应用中实现实时转录" →

git clone https://github.com/deepgram-starters/node-live-transcription.git

"我想在Go服务中添加文字转语音功能" →

git clone https://github.com/deepgram-starters/go-text-to-speech.git

"我想用C#分析音频情感" →

git clone https://github.com/deepgram-starters/csharp-text-intelligence.git

All Starters

所有启动模板

	transcription	live-transcription	text-to-speech	live-text-to-speech	text-intelligence	voice-agent	flux
node	repo	repo	repo	repo	repo	repo	repo
bun	repo	repo	repo	repo	repo	repo	repo
deno	repo	repo	repo	repo	repo	repo	repo
fastapi	repo	repo	repo	repo	repo	repo	repo
flask	repo	repo	repo	repo	repo	repo	repo
django	repo	repo	repo	repo	repo	repo	repo
go	repo	repo	repo	repo	repo	repo	repo
java	repo	repo	repo	repo	repo	repo	repo
csharp	repo	repo	repo	repo	repo	repo	repo
rust	repo	repo	repo	repo	repo	repo	repo
ruby	repo	repo	repo	repo	repo	repo	repo
php	repo	repo	repo	repo	repo	repo	repo
cpp	repo	repo	repo	repo	repo	repo	repo

	transcription	live-transcription	text-to-speech	live-text-to-speech	text-intelligence	voice-agent	flux
node	repo	repo	repo	repo	repo	repo	repo
bun	repo	repo	repo	repo	repo	repo	repo
deno	repo	repo	repo	repo	repo	repo	repo
fastapi	repo	repo	repo	repo	repo	repo	repo
flask	repo	repo	repo	repo	repo	repo	repo
django	repo	repo	repo	repo	repo	repo	repo
go	repo	repo	repo	repo	repo	repo	repo
java	repo	repo	repo	repo	repo	repo	repo
csharp	repo	repo	repo	repo	repo	repo	repo
rust	repo	repo	repo	repo	repo	repo	repo
ruby	repo	repo	repo	repo	repo	repo	repo
php	repo	repo	repo	repo	repo	repo	repo
cpp	repo	repo	repo	repo	repo	repo	repo

Need something more specific?

需要更特定的资源？

Focused feature snippets (one feature, one language, < 50 lines) →
```
recipes
```
skill → https://github.com/deepgram/recipes
Third-party integrations (Twilio, LiveKit, LangChain, Vercel AI SDK, Discord, etc.) →
```
examples
```
skill → https://github.com/deepgram/examples
SDK-specific code skills (idiomatic imports, async patterns, gotchas) →
```
npx skills add deepgram/deepgram-{lang}-sdk
```
— see the
```
api
```
skill for the full list of 9 SDKs.

聚焦功能的代码片段（单一功能、单一语言、少于50行代码）→
```
recipes
```
技能 → https://github.com/deepgram/recipes
第三方集成示例（Twilio、LiveKit、LangChain、Vercel AI SDK、Discord等）→
```
examples
```
技能 → https://github.com/deepgram/examples
SDK专属代码技能（规范导入、异步模式、常见陷阱）→
```
npx skills add deepgram/deepgram-{lang}-sdk
```
— 查看
```
api
```
技能获取全部9个SDK的完整列表。