0
# Multimodal APIs
1

2
Image generation, audio processing (speech-to-text, text-to-speech, translation), and content moderation capabilities with OpenAI compatibility.
3

4
## Capabilities
5

6
### Image Generation
7

8
```python { .api }
9
class Images:
10
    def generate(self, **kwargs): ...
11
    def create_variation(self, **kwargs): ...
12
    def edit(self, **kwargs): ...
13
```
14

15
### Audio Processing
16

17
```python { .api }
18
class Audio:
19
    transcriptions: Transcriptions
20
    translations: Translations
21
    speech: Speech
22

23
class Transcriptions:
24
    def create(self, **kwargs): ...
25

26
class Translations:
27
    def create(self, **kwargs): ...
28

29
class Speech:
30
    def create(self, **kwargs): ...
31
```
32

33
### Content Moderation
34

35
```python { .api }
36
class Moderations:
37
    def create(self, **kwargs): ...
38
```
39

40
## Usage Examples
41

42
```python
43
from portkey_ai import Portkey
44

45
portkey = Portkey(
46
    api_key="PORTKEY_API_KEY",
47
    virtual_key="VIRTUAL_KEY"
48
)
49

50
# Generate image
51
image = portkey.images.generate(
52
    prompt="A cat in a spacesuit",
53
    model="dall-e-3",
54
    size="1024x1024"
55
)
56

57
# Transcribe audio
58
transcription = portkey.audio.transcriptions.create(
59
    file=open("audio.mp3", "rb"),
60
    model="whisper-1"
61
)
62

63
# Moderate content
64
moderation = portkey.moderations.create(
65
    input="This is a test message"
66
)
67
```