Qwen/Qwen3-TTS-VoiceDesign

deepinfra/Qwen/Qwen3-TTS-VoiceDesign

audioContext —

● Qwen3-TTS-VoiceDesign is a voice design variant of Qwen3-TTS by Alibaba's Qwen team. Instead of selecting from preset voices, you describe the voice you want in natural language — and the model generates speech in that voice. Key capabilities: - Natural language voice control — describe any voice with free text (e.g. "a deep male voice with a calm, authoritative presence", "a young cheerful female with a warm and friendly tone") - 10 languages — English, Chinese, Japanese, Korean, German, French, Russian, Spanish, Italian, Portuguese - Streaming support — real-time PCM streaming - Multiple output formats — WAV, MP3, FLAC, PCM Built on the same 1.7B parameter architecture as Qwen3-TTS, using discrete multi-codebook language modeling and a custom 12Hz acoustic tokenizer for high-quality end-to-end speech synthesis.

Price

Price$20

per character

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

Provider	Tag	Quant	Input	Output	Context	Uptime	Status	Source
DeepInfra	—	—	Not published—	Not published—	—	—	Listed	deepinfra

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

Input tokens Output tokens Units

No published price at list price for this workload

Every rate

Unit	Input	Output	Flat	Confidence
character	$20/character	Not published—	Not published—	official

Price history

Qwen/Qwen3-TTS-VoiceDesign

input or flat output

Daily snapshots

UTC date	Unit	Input	Output	Flat
2026-10-08	character	$20	Not published—	Not published—
2026-10-09	character	$20	Not published—	Not published—
2026-10-10	character	$20	Not published—	Not published—
2026-10-11	character	$20	Not published—	Not published—
2026-10-12	character	$20	Not published—	Not published—
2026-10-13	character	$20	Not published—	Not published—
2026-10-14	character	$20	Not published—	Not published—
2026-10-15	character	$20	Not published—	Not published—
2026-10-16	character	$20	Not published—	Not published—
2026-10-17	character	$20	Not published—	Not published—
2026-10-18	character	$20	Not published—	Not published—
2026-10-19	character	$20	Not published—	Not published—
2026-10-20	character	$20	Not published—	Not published—
2026-10-21	character	$20	Not published—	Not published—
2026-10-22	character	$20	Not published—	Not published—
2026-10-23	character	$20	Not published—	Not published—
2026-10-24	character	$20	Not published—	Not published—
2026-10-25	character	$20	Not published—	Not published—
2026-10-26	character	$20	Not published—	Not published—
2026-10-27	character	$20	Not published—	Not published—
2026-10-28	character	$20	Not published—	Not published—
2026-10-29	character	$20	Not published—	Not published—
2026-10-30	character	$20	Not published—	Not published—

Alternatives

bosonai/HiggsAudioV2.5$20/character · Compare
Qwen/Qwen3-TTS$20/character · Compare
inworld-ai/realtime-tts-1.5-mini$25/character · Compare
Orpheus 3B 0.1 FT$15/1M · Compare
sesame/csm-1b$7/character · Compare
Audio8/Audio8-TTS-Preview-0.6b$5/character · Compare

Parameters (1)

tts

Call this model

OpenRouter id deepinfra/Qwen/Qwen3-TTS-VoiceDesign. InferenceList does not send the request.

curl

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepinfra/Qwen/Qwen3-TTS-VoiceDesign","messages":[{"role":"user","content":"Hello"}]}'

JavaScript

await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "deepinfra/Qwen/Qwen3-TTS-VoiceDesign",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python

import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "deepinfra/Qwen/Qwen3-TTS-VoiceDesign", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON