Models / Qwen
Qwen3 TTS VoiceDesign
by Qwen
Reads your text aloud.
Qwen3 TTS VoiceDesign turns written text into spoken audio. It is made by Qwen. On Tīrtha it reads up to 4,000 characters per call.
Price per 1M characters
The live price, read from billing as this page loads. You pay for the characters of text you send, from prepaid credit. There is no charge for the audio it returns. Requests that fail are not charged.
Live price not available just now.
tirtha/qwen3-tts-voicedesignGood at
- Describe the voiceYou describe the voice you want in words, and the model designs it. No reference recording is used.
- Ten languagesThe same ten languages as Qwen3-TTS.
- Tone controlThe maker says it follows instructions for timbre, emotion and pace.
Model card details
- Made by
- Qwen
- Kind
- Text to speech
- Licence
- Apache-2.0
- Listed on Hugging Face
- Jan 21, 2026
- Languages
- Chinese, English, Japanese, Korean, German, French, Russian, Portuguese and 2 more
- Parameters
- 1.7 billion
- Languages
- 10
- Voice
- Designed from a text description, up to 200 characters on Tīrtha
Hear it
Made with Qwen3 TTS VoiceDesign. Real outputs, not edited, each with the exact text it read and the voice it used.
Welcome back. Your order shipped this morning and should arrive on Friday. Reply to this message if you need anything else.AI-generated
Welcome back. Your tea is ready and the fire is warm.AI-generated
Three, two, one, and the rocket lifts into a clear blue sky.AI-generated
Open weights, Apache-2.0 licence. Maker facts from Qwen's model card on Hugging Face (huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign). Limits are the ones Tīrtha enforces today.
Request and response
Fields you send
| Field | Required | Values |
|---|---|---|
model | yes | tirtha/qwen3-tts-voicedesign |
input | yes | The text to speak, 1 to 4,000 characters. |
voice_description | yes | The voice you want, described in words, 1 to 200 characters. Send no voice: this model refuses one. Do not describe a real, identifiable person's voice. |
response_format | no | wav only, which is the default. |
Fields not in this table are refused with unknown_parameter. That includes speed, which no model here takes.
What comes back
HTTP/1.1 200 OK
Content-Type: audio/wav
Cache-Control: no-store
<the wav audio file, as bytes>The body is the audio file itself, ready to save or play. There is no JSON wrapper and no link to fetch. You are billed for the characters of input you sent.
If something goes wrong
Errors come back as JSON: {"error": {"code", "message", "type"}}. A call that fails is not charged.
| HTTP | Code | What it means |
|---|---|---|
| 400 | invalid_input | The text is empty or over the limit: split it. |
| 400 | invalid_voice_description | The description is empty or over the limit. |
| 400 | invalid_voice | A voice was sent: this model takes a voice_description instead. |
| 400 | invalid_response_format | Only wav is served. |
| 400 | unknown_parameter | A field the API does not take. Send only the fields above. |
| 400 | invalid_request | The body is not a JSON object. |
| 400 | content_policy | Refused by content policy. Nothing was charged. |
| 400 | request_rejected | The request was rejected. Nothing was charged. |
| 402 | billing_required | This needs a prepaid credit account. Add credits in your dashboard first. |
| 402 | insufficient_credits | Not enough prepaid credit for this request. The message says how much it may need. |
| 404 | model_not_found | The model id is wrong, or is not this kind of model. |
| 404 | model_not_priced | This model is not available yet. |
| 429 | media_busy | This model is busy right now. Retry in a few seconds. Nothing was charged. |
| 503 | billing_unavailable | Billing is temporarily unavailable. Please retry. |
| 503 | unavailable | Temporarily unavailable. Nothing was charged. |
What a job costs
An article of about 1,000 words (6,000 characters) costs about -
Worked out from the live price above, at about 6 characters a word, counting spaces. Punctuation counts too.
How to use it
Pick it when no preset voice fits and you would rather describe the voice in a sentence.
Model id tirtha/qwen3-tts-voicedesign · POST https://api.tirtha.ai/v1/audio/speech
- One call reads up to 4,000 characters. For longer text, split it at the end of a sentence, make one call per part, and play or join the files in order. The Python example does the splitting, and cuts a single over-long sentence at a space.
- Describe the voice in
voice_description, up to 200 characters: who is speaking, their age and tone, and the pace. For examplea calm, clear adult narrator voice. Change the words to get a different voice. Do not describe a real, identifiable person's voice. - The audio comes back as WAV, the only format served, so
response_formatcan be left out. WAV keeps full quality; convert it on your side if you need a smaller file. - The response body is the audio file. Save it straight to disk with the right extension, or stream it to a player.
- Check how the voice reads numbers, dates and short forms such as 10:30 or Dr. Write them out the way they should sound if it matters.
- Tell your listeners the voice is AI-generated, for example in your app or at the start of the audio.
Set TIRTHA_API_KEY to a key from your dashboard first. Keys, credits and the base URL: Quickstart.