Free tier available
No credit card required

Generate Realistic Voiceovers

High-quality TTS in dozens of voices and languages.

Get $5 credits Docs

Text-to-Speech Qwen3 TTS VoiceClone

Pricing Advanced

Reference text (transcript of the reference audio)

Target text (text to synthesise)

Reference audio Click or drop a voice file Popular audio formats · 5–30s of clean speech recommended

Uploading…

I confirm I have the right to clone this voice.

Estimated cost: calculating… $0.00248/clip

2 free clips left

{
    "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/v2/audio/speech' \
  -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.'

Related Models

Built for developers who need power without complexity.

Qwen3 TTS CustomVoice

9 premium voices (male & female). 10 languages: EN, ZH, JA, KO, DE, FR, RU, PT, ES, IT. Instruction-driven emotion & prosody control. Streaming with 97ms latency. Output: MP3 at 24kHz.

$0.0026/req

Qwen3 TTS VoiceDesign

Design a unique voice from a text description — define tone, accent, age, and emotion without any audio samples.

$0.77/1M chars

Chatterbox

23 languages: EN, ES, FR, DE, ZH, JA, KO, AR, HI, PL and more. Emotion exaggeration control. Built-in AI watermarking. Output: MP3/WAV/FLAC.

$0.0015/req

Kokoro

41 voices (male & female). 7 languages: EN-US, EN-GB, ES, FR-FR, HI, IT, PT-BR. Output: MP3/FLAC at 24kHz.

$0.0002/req

Free tier available
No credit card required

Get More AI Power
Pay Less

Get $5 credits Docs

Join developers & vibe coders building AI apps with deAPI. No credit card, zero setup headaches — just pure, instant AI magic.

Need enterprise pricing or SLA? Talk to Sales

You've reached your free daily limit

Your counter resets at 00:00 UTC.

Want to keep going? Register now and get $5 in free credits to start.