Hudson’s REST API provides the core for your audio pipeline. Seamlessly integrate our intelligent processing capabilities to orchestrate studio-quality audio within your own audio native products.
/v1/audio/ttsGenerate studio-quality speech from text with voice cloning. Supports 80+ languages and custom voice profiles.
curl -X POST https://api.hudson-ai.com/v1/audio/tts \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome to Hudson AI Studio.",
"voice_id": "voice_abc123",
"language": "en",
"emotion": "neutral"
}'/v1/audio/vcConvert voice characteristics from one speaker to another while preserving prosody, timing, and emotional tone.
curl -X POST https://api.hudson-ai.com/v1/audio/vc \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "audio=@source.wav" \
-F "target_voice_id=voice_xyz789" \
-F "preserve_emotion=true"/v1/audio/separateSeparate audio tracks into individual components: dialogue, music, sound effects, and background ambience.
curl -X POST https://api.hudson-ai.com/v1/audio/separate \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "audio=@mixed_track.wav" \
-F "stems=dialogue,music,sfx"/v1/audio/transcribeMulti-speaker transcription with speaker diarization, timestamps, and confidence scores across 80+ languages.
curl -X POST https://api.hudson-ai.com/v1/audio/transcribe \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "audio=@interview.wav" \
-F "language=en" \
-F "diarize=true"Request API access and get your credentials to start building with Hudson AI Studio.
Get API Access