Voice Text to Speech FairStack (Self-hosted)

Qwen3-TTS 1.7B

Qwen3-TTS 1.7B costs $0.0060/req on FairStack — a text to speech model for Custom voice creation, Voice design experimentation, Default TTS generation. No subscription required. Pay per generation with full REST API access. FairStack applies a transparent 20% margin on infrastructure cost so you always see the real price.

FairStack price
$0.0060/req

What is Qwen3-TTS 1.7B?

Qwen3-TTS is FairStack's default text-to-speech model, offering a unique dual capability: voice design from text descriptions and voice cloning from reference audio. In voice design mode, users describe the desired voice characteristics in natural language, and the model generates matching speech without any reference audio needed. The voice design capability is particularly distinctive. Rather than choosing from a preset library, users can describe a voice as they imagine it, and the model creates speech matching that description. Clone mode requires both reference audio and a reference text transcript for best results. Self-hosting provides cost advantages and privacy. Compared to IndexTTS2 which offers higher cloning fidelity, Qwen3-TTS's voice design mode provides a capability no other model on the platform offers. Against preset-based models like Kokoro with 54 fixed voices, voice design offers unlimited vocal variety. As the default TTS model, it is well-tested across diverse use cases. Best suited for custom voice creation, voice design experimentation, and general TTS generation where the flexibility to either design a voice from description or clone from audio provides maximum creative control. Available on FairStack at infrastructure cost plus a 20% platform fee.

Key Features

Voice design from text description
Voice cloning with reference audio
Natural prosody
Self-hosted

What are Qwen3-TTS 1.7B's strengths?

Unique voice design capability
Good multilingual support
Default model — well-tested

What are Qwen3-TTS 1.7B's limitations?

Clone mode requires ref_text transcript
No built-in preset voices

What is Qwen3-TTS 1.7B best for?

Custom voice creation Voice design experimentation Default TTS generation

How much does Qwen3-TTS 1.7B cost?

Metric
FairStack
Details
Price per generation
$0.0060
Includes 20% margin
Per-character rate
$0.000010/char
Min $0.0030/req
Subscription
None
Pay per generation only

Example Outputs

Generated with Qwen3-TTS 1.7B on FairStack

Good morning everyone. Today we cover the fundamentals of machine learning, from neural networks to transformer architectures.

Every pixel, every note, every word is generated at cost plus a small transparent margin. No subscriptions. No gatekeeping.

How do I use the Qwen3-TTS 1.7B API?

curl
curl -X POST https://api.fairstack.ai/v1/generations/voice \
  -H "Authorization: Bearer $FAIRSTACK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-3-tts",
    "prompt": "Good morning everyone. Today we cover the fundamentals of machine learning, from neural networks to transformer architectures."
  }'
Python
import requests

response = requests.post(
    "https://api.fairstack.ai/v1/generations/voice",
    headers={
        "Authorization": f"Bearer {FAIRSTACK_API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "model": "qwen-3-tts",
        "prompt": "Good morning everyone. Today we cover the fundamentals of machine learning, from neural networks to transformer architectures.",
    },
)

result = response.json()
print(result["url"])
Node.js
const response = await fetch(
  "https://api.fairstack.ai/v1/generations/voice",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.FAIRSTACK_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      model: "qwen-3-tts",
      prompt: "Good morning everyone. Today we cover the fundamentals of machine learning, from neural networks to transformer architectures.",
    }),
  }
);

const result = await response.json();
console.log(result.url);

Frequently Asked Questions

How much does Qwen3-TTS 1.7B cost?

Qwen3-TTS 1.7B costs $0.0060/req on FairStack as of 2026-03-23. This price includes FairStack's transparent 20% margin on infrastructure cost. No subscription or monthly fee — you pay per generation only. Minimum deposit is $1.

What is Qwen3-TTS 1.7B and what is it best for?

Qwen3-TTS is FairStack's default text-to-speech model, offering a unique dual capability: voice design from text descriptions and voice cloning from reference audio. In voice design mode, users describe the desired voice characteristics in natural language, and the model generates matching speech without any reference audio needed. The voice design capability is particularly distinctive. Rather than choosing from a preset library, users can describe a voice as they imagine it, and the model creates speech matching that description. Clone mode requires both reference audio and a reference text transcript for best results. Self-hosting provides cost advantages and privacy. Compared to IndexTTS2 which offers higher cloning fidelity, Qwen3-TTS's voice design mode provides a capability no other model on the platform offers. Against preset-based models like Kokoro with 54 fixed voices, voice design offers unlimited vocal variety. As the default TTS model, it is well-tested across diverse use cases. Best suited for custom voice creation, voice design experimentation, and general TTS generation where the flexibility to either design a voice from description or clone from audio provides maximum creative control. Available on FairStack at infrastructure cost plus a 20% platform fee. Qwen3-TTS 1.7B is best for Custom voice creation, Voice design experimentation, Default TTS generation. Available via FairStack's REST API with curl, Python, and Node.js SDKs.

Does Qwen3-TTS 1.7B have an API?

Yes. Qwen3-TTS 1.7B is available via FairStack's REST API at api.fairstack.ai. Send a POST request to /v1/generations/voice with your API key and prompt. Works with curl, Python requests, Node.js fetch, and any HTTP client. No SDK installation required.

How does Qwen3-TTS 1.7B compare to other voice models?

Qwen3-TTS 1.7B excels at Custom voice creation, Voice design experimentation, Default TTS generation. It is a text to speech model priced at $0.0060/req on FairStack. Key strengths: Unique voice design capability, Good multilingual support. Compare all voice models at fairstack.ai/models.

What makes Qwen3-TTS stand out from other voice models?

Qwen3-TTS excels with unique voice design capability and good multilingual support.

What are the known limitations of Qwen3-TTS?

Key limitations include: clone mode requires ref_text transcript; no built-in preset voices. FairStack documents these transparently so you can choose the right model for your workflow.

What voice features does Qwen3-TTS support?

Qwen3-TTS offers: voice design from text description; voice cloning with reference audio; natural prosody; self-hosted. All capabilities are accessible through both the FairStack web interface and REST API.

Start using Qwen3-TTS 1.7B today

$0.0060/req. Full API access. No subscription.

Start Creating