Overview

Nola Translator turns speech into real-time captions and translations. Run speech recognition and translation locally, use cloud services, or combine the two.

Features

• Local models: Run recognition models such as Qwen3-ASR and SenseVoiceSmall, and translation models such as HY-MT2 locally. The app can also search for and install other models from Hugging Face.
• Cloud models: Use speech recognition from Aliyun, MiniMax, and other providers; connect translation models through LLM protocols such as OpenAI-compatible APIs, Anthropic, or Ollama; or use the free MyMemory translation service.
• GPU acceleration: Detects available compute devices and lets you configure separate devices for recognition and translation.
• Browser extension: Includes a browser extension for Chrome and Edge that displays bilingual captions on video pages. You can also configure desktop system audio as an input source.
• Real-time caption overlay: Supports system output, a selected audio device, or a microphone. Captions appear in a separate overlay, where you can adjust its position, font size, colors, opacity, and original/translated text layout.
• Flexible configuration: Install models as needed and choose recognition and translation methods, language directions, compute devices, and caption styles. API credentials are securely stored by the app.
• History and export: Save caption history and export it as TXT, SRT, or WebVTT. Audio recording can be enabled optionally.

Interface Preview

Home	Floating Captions	Video Captions

Local Model Installation	Inference Environment Settings	Dark Mode Support

The floating and browser caption scenes use a cropped frame from Tears of Steel, © Blender Foundation, under CC BY 3.0.

Installation

• Download the latest release

Windows x64 is supported. You can choose the EXE or MSI installer. Support for other platforms is planned once development has stabilized.

• Online documentation

Local Recognition Models

[!TIP] The languages available for recognition and translation depend on the selected model's capabilities. The tables below show the capabilities of the recommended models included in the app. If you have a model to recommend, submit it as an issue; we will evaluate it for possible inclusion. For first-time users, we recommend SenseVoiceSmall for recognition and HY-MT2 for translation.

Model	Number of Languages	Details
Qwen3-ASR	30	Chinese, English, Cantonese, Arabic, German, French, Spanish, Portuguese, Indonesian, Italian, Korean, Russian, Thai, Vietnamese, Japanese, Turkish, Hindi, Malay, Dutch, Swedish, Danish, Finnish, Polish, Czech, Filipino, Persian, Greek, Hungarian, Macedonian, and Romanian
SenseVoiceSmall	5	Chinese, English, Cantonese, Japanese, and Korean
Fun-ASR Nano	4	Chinese, English, Japanese, and Cantonese
VibeVoice-ASR	48	English, Chinese, Spanish, Portuguese, German, Japanese, Korean, French, Russian, Indonesian, Swedish, Italian, Hebrew, Dutch, Polish, Norwegian, Turkish, Thai, Arabic, Hungarian, Catalan, Czech, Danish, Persian, Afrikaans, Hindi, Finnish, Estonian, Greek, Romanian, Vietnamese, Bulgarian, Icelandic, Slovenian, Slovak, Lithuanian, Swahili, Ukrainian, Latvian, Croatian, Nepali, Serbian, Filipino, Malay, Urdu, Mongolian, Armenian, and Javanese
MiMo-V2.5-ASR	3	Chinese, English, and Cantonese

Local Translation Models

Model	Number of Languages	Details
HY-MT2	38	Simplified Chinese, Traditional Chinese, English, French, Portuguese, Spanish, Japanese, Turkish, Russian, Arabic, Korean, Thai, Italian, German, Vietnamese, Malay, Indonesian, Filipino, Hindi, Polish, Czech, Dutch, Khmer, Burmese, Persian, Gujarati, Urdu, Telugu, Marathi, Hebrew, Bengali, Tamil, Ukrainian, Tibetan, Kazakh, Mongolian, Uyghur, and Cantonese
M2M100 418M	100	Afrikaans, Amharic, Arabic, Asturian, Azerbaijani, Bashkir, Belarusian, Bulgarian, Bengali, Breton, Bosnian, Catalan, Cebuano, Czech, Welsh, Danish, German, Greek, English, Spanish, Estonian, Persian, Fula, Finnish, French, Western Frisian, Irish, Scottish Gaelic, Galician, Gujarati, Hausa, Hebrew, Hindi, Croatian, Haitian Creole, Hungarian, Armenian, Indonesian, Igbo, Ilocano, Icelandic, Italian, Japanese, Javanese, Georgian, Kazakh, Khmer, Kannada, Korean, Luxembourgish, Ganda (Luganda), Lingala, Lao, Lithuanian, Latvian, Malagasy, Macedonian, Malayalam, Mongolian, Marathi, Malay, Burmese, Nepali, Dutch, Norwegian, Northern Sotho, Occitan, Odia, Punjabi, Polish, Pashto, Portuguese, Romanian, Russian, Sindhi, Sinhala, Slovak, Slovenian, Somali, Albanian, Serbian, Swati, Sundanese, Swedish, Swahili, Tamil, Thai, Filipino, Tswana, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese, Wolof, Xhosa, Yiddish, Yoruba, Chinese, and Zulu
Index-Translate	150	English, Chinese, German, French, Spanish, Japanese, Korean, Portuguese, Russian, Arabic, Italian, Dutch, Polish, Romanian, Swedish, Turkish, Hindi, Vietnamese, Thai, Indonesian, Malay, Filipino, Ukrainian, Persian, Czech, Greek, Danish, Hungarian, Finnish, Norwegian (written), Slovak, Bulgarian, Bosnian, Catalan, Bengali, Hebrew, Lithuanian, Slovenian, Estonian, Albanian, Latvian, Azerbaijani, Croatian, Tamil, Nepali, Urdu, Macedonian, Serbian (Cyrillic), Marathi, Georgian, Malayalam, Kazakh, Icelandic, Galician, Kannada, Moroccan Arabic, Gujarati, Belarusian, Afrikaans, Armenian, Mongolian, Khmer, Basque, Burmese, Latin, Uzbek (Cyrillic), Telugu, Odia, Norwegian Nynorsk, Uzbek, Swahili, Sinhala, Kyrgyz, Somali, Punjabi, Egyptian Arabic, Welsh, Norman, Pashto, Irish, Serbian (Latin), Hausa, Kurdish (Sorani), Maltese, Cantonese, Tajik, Kurdish (Kurmanji), Betawi, Amharic, Lao, Luxembourgish, Frisian, Divehi, Esperanto, Kinyarwanda, Najdi Arabic, Faroese, Malagasy, Assamese, Sindhi, Xhosa, Turkmen, Haitian Creole, Scottish Gaelic, Cebuano, Yiddish, Javanese, Bashkir, Papiamento, Maori, Uyghur, Tatar, Tibetan, Hmong, Western Armenian, Yoruba, Zulu, Southern Kurdish, Samoan, Corsican, Fiji Hindi, Sundanese, Chichewa, Igbo, Hawaiian, Sesotho, Mizo, Shona, Chuvash, South Azerbaijani, Romansh, Rundi, Hindi (Latin), Sakha, Tigrinya, Asturian, Occitan, Hakha Chin, Northern Sami, Low German, Ossetian, Urdu (Latin), Swiss German, Angika, Levantine Arabic, Oromo, Neapolitan, Upper Sorbian, Hiligaynon, and Greenlandic

Local Text-to-Speech

Model	Number of Languages	Details
Qwen3-TTS	10	Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian

Cloud Recognition Models

Provider	Model	Supported languages	Details
Aliyun	Qwen3.5 / Qwen3.8 LiveTranslate	60	Chinese, English, Arabic, German, French, Spanish, Portuguese, Indonesian, Italian, Korean, Russian, Thai, Vietnamese, Japanese, Turkish, Hindi, Malay, Dutch, Urdu, Norwegian Bokmål, Swedish, Danish, Hebrew, Finnish, Polish, Icelandic, Czech, Filipino, Persian, Cantonese, Greek, Afrikaans, Asturian, Belarusian, Bulgarian, Bengali, Bosnian, Catalan, Cebuano, Estonian, Galician, Gujarati, Croatian, Hungarian, Javanese, Kazakh, Kannada, Kyrgyz, Latvian, Macedonian, Malayalam, Marathi, Punjabi, Romanian, Slovak, Slovenian, Swahili, Tajik, Azerbaijani, and Ukrainian. Version 3.8 detects the source language automatically; version 3.5 allows you to specify the source language.
MiniMax	Speech-to-Text asr-1.0	20	Arabic, Cantonese, Chinese, English, Filipino, French, German, Indonesian, Italian, Japanese, Korean, Malay, Polish, Portuguese, Russian, Spanish, Thai, Turkish, Ukrainian, and Vietnamese.

Cloud Translation Models

Model	Number of Languages	Details
Aliyun LiveTranslate	60	Automatic source-language detection
Index-Translate-35B-A3B	150	English, Chinese, German, French, Spanish, Japanese, Korean, Portuguese, Russian, Arabic, Italian, Dutch, Polish, Romanian, Swedish, Turkish, Hindi, Vietnamese, Thai, Indonesian, Malay, Filipino, Ukrainian, Persian, Czech, Greek, Danish, Hungarian, Finnish, Norwegian (written), Slovak, Bulgarian, Bosnian, Catalan, Bengali, Hebrew, Lithuanian, Slovenian, Estonian, Albanian, Latvian, Azerbaijani, Croatian, Tamil, Nepali, Urdu, Macedonian, Serbian (Cyrillic), Marathi, Georgian, Malayalam, Kazakh, Icelandic, Galician, Kannada, Moroccan Arabic, Gujarati, Belarusian, Afrikaans, Armenian, Mongolian, Khmer, Basque, Burmese, Latin, Uzbek (Cyrillic), Telugu, Odia, Norwegian Nynorsk, Uzbek, Swahili, Sinhala, Kyrgyz, Somali, Punjabi, Egyptian Arabic, Welsh, Norman, Pashto, Irish, Serbian (Latin), Hausa, Kurdish (Sorani), Maltese, Cantonese, Tajik, Kurdish (Kurmanji), Betawi, Amharic, Lao, Luxembourgish, Frisian, Divehi, Esperanto, Kinyarwanda, Najdi Arabic, Faroese, Malagasy, Assamese, Sindhi, Xhosa, Turkmen, Haitian Creole, Scottish Gaelic, Cebuano, Yiddish, Javanese, Bashkir, Papiamento, Maori, Uyghur, Tatar, Tibetan, Hmong, Western Armenian, Yoruba, Zulu, Southern Kurdish, Samoan, Corsican, Fiji Hindi, Sundanese, Chichewa, Igbo, Hawaiian, Sesotho, Mizo, Shona, Chuvash, South Azerbaijani, Romansh, Rundi, Hindi (Latin), Sakha, Tigrinya, Asturian, Occitan, Hakha Chin, Northern Sami, Low German, Ossetian, Urdu (Latin), Swiss German, Angika, Levantine Arabic, Oromo, Neapolitan, Upper Sorbian, Hiligaynon, and Greenlandic
Microsoft Translator	100+	Per the official language table
Google Translate	100+	Per the official language table
MyMemory (free translation)	100+	Per the official language table
LLM API (OpenAI-compatible, Anthropic, Ollama)	Depends on the chosen model	—

LLM API Configuration

[!TIP] The LLM protocols here are used for translation. Aliyun and MiniMax ASR models use separate connection settings and credentials under Audio and Recognition. Local models require no API configuration.

Supported Protocols

The app supports the following API protocols:

Protocol
OpenAI Chat Completions
OpenAI Responses
Anthropic Messages
Ollama Chat

Configuration Examples

Provider	API Format	Example API URL	Example Model ID
DeepSeek	OpenAI Chat Completions	https://api.deepseek.com	deepseek-flash
MiniMax	OpenAI Chat Completions	https://api.minimax.io/v1	MiniMax-M3
MiMo	OpenAI Chat Completions	https://api.xiaomimimo.com/v1	mimo-v2.6-pro

Configuration Steps

1. Select Cloud Translation in the translation settings.
2. Choose the API format supported by your provider.
3. Enter the API URL, API key, and model ID.
4. Adjust the context window and maximum output tokens as needed.

Project Structure

assets/brand/                  Logo and brand assets
docs/                          VitePress product website and multilingual documentation
engine/nola_translator_engine/  Python audio, recognition, and translation engine
engine/tests/                   Python tests
scripts/                        Setup and build scripts
src/main/                       Electron main process
src/preload/                    IPC bridge
src/renderer/                   React interface
src/shared/                     Shared contracts and settings
tests/                          Application tests

Development and Build

npm run typecheck
npm test
.\.venv\Scripts\python.exe -m pytest engine\tests
npm run build

Build the Windows x64 installer:

npm run dist:win

Contributing

Fork the repository, create a branch, make your changes, and open a pull request. Briefly describe your changes and the checks you ran. For design and code conventions, see DESIGN.md and the contribution guide.

Sponsorship

You can support this project through the channels below. Sponsors receive benefits including priority help with issues, one-on-one guidance, permanent recognition in the sponsor list and in the app, and custom features.

1. Mainland China

• Afdian

2. Other regions

• GitHub Sponsors

License

Nola Translator's original code is licensed under GNU GPL v3.0 only. Third-party components and models are subject to their respective licenses; see Third-Party Notices.