Qwen3 TTS VoiceClone
Text-to-Speech
Estimated cost: $0.002481/speech
2
free speechs left
Reference Text (Transcript of the reference audio)
Target Text (Text to synthesize with cloned voice)
Voice file
{
"mode": "voice_clone",
"model": "Qwen3_TTS_12Hz_1_7B_Base",
"text": "The possibilities are endless. From a single line of text, create anything you can imagine. Voices that feel real. Music that moves you. Images that inspire. Welcome to the new era of creation.",
"lang": "English",
"speed": 1,
"format": "mp3",
"sample_rate": 24000,
"ref_audio": "(binary file)",
"ref_text": "Welcome to the future of AI. What once took hours now takes seconds. Generate images, music, video, and speech, all from a single API. This is deAPI."
}
curl -X POST \
'https://api.deapi.ai/api/v1/client/txt2audio' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {{ YOUR_API_TOKEN }}' \
-F 'mode=voice_clone' \
-F 'model=Qwen3_TTS_12Hz_1_7B_Base' \
-F 'text=The possibilities are endless. From a single line of text, create anything you can imagine. Voices that feel real. Music that moves you. Images that inspire. Welcome to the new era of creation.' \
-F 'lang=English' \
-F 'speed=1' \
-F 'format=mp3' \
-F 'sample_rate=24000' \
-F 'ref_audio=@/path/to/reference.wav' \
-F 'ref_text=Welcome to the future of AI. What once took hours now takes seconds. Generate images, music, video, and speech, all from a single API. This is deAPI.'
Estimated cost: $0.002481/speech
2
free speechs left
Reference Text (Transcript of the reference audio)
Target Text (Text to synthesize with cloned voice)
Voice file