APIs have been supported by this library. Update to support latest models. Now you can use the API to create speech and generate images with Dall-E 3.
- Chat
- Images
- Audio
- TTS
- STT
- Models
- Edits
- Completions
- Embeddings
- Files
- Fine-tunes
- Moderations
- Engines
final client = OpenaiClient(
config: OpenaiConfig(
apiKey: Env.apiKey, // your api key from openai.com
baseUrl: Env.baseUrl, // you can set your reverse proxy api
httpProxy: Env.httpProxy, // if you need access api through http proxy
),
);
- Audio Transcription
final result = await client.createTranscription(
TranscriptionRequest(
file: 'assets/ttsmaker-file-2023-3-22-14-57-0.mp3',
),
);
print(result.text);
- Audio Translation
final translateResult = await client.createTraslation(
TranslationRequest(
file: 'assets/ttsmaker-file-2023-3-22-17-27-30.mp3',
// file: "assets/ttsmaker-file-2023-3-22-14-2-35.mp3",
// Wierd. this will be translated into Pinyin for Chinese if prompt not set.
// 你好朋友,我好想你。
// Ni Hao Peng You, Wo Hao Xiang Ni
// prompt: "Please translate into Chinese.",
),
);
Thanks goes to these wonderful people:
Contributions of any kind welcome!