Qwen 3 TTS - Text to Speech [1.7B]

Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model

Inference$ Commercial useFrom 2 credits per run

About Qwen 3 TTS - Text to Speech [1.7B]

Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model

text-to-speech

Pricing

A run with the default settings costs 2 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

texttextarearequired

The text to be converted to speech.

prompttextarea

Optional prompt to guide the style of the generated speech. This prompt will be ignored if a speaker embedding is provided.

voiceselect

The voice to be used for speech synthesis, will be ignored if a speaker embedding is provided. Check out the **[documentation](https://github.com/QwenLM/Qwen3-TTS/tree/main?tab=readme-ov-file#custom-voice-generate)** for each voice's details and which language they primarily support.

Options: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee

languageselectdefault: "Auto"

The language of the voice.

Options: Auto, English, Chinese, Spanish, French, German, Italian, Japanese, Korean, Portuguese, Russian

speaker_voice_embedding_file_urlfile

URL to a speaker embedding file in safetensors format, from `fal-ai/qwen-3-tts/clone-voice` endpoint. If provided, the TTS model will use the cloned voice for synthesis instead of the predefined voices.

reference_texttextarea

Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.

top_kintegerdefault: 50

Top-k sampling parameter.

top_pnumberdefault: 1

Top-p sampling parameter.

temperaturenumberdefault: 0.9

Sampling temperature; higher => more random.

repetition_penaltynumberdefault: 1.05

Penalty to reduce repeated tokens/codes.

subtalker_dosamplebooleandefault: true

Sampling switch for the sub-talker.

subtalker_top_kintegerdefault: 50

Top-k for sub-talker sampling.

subtalker_top_pnumberdefault: 1

Top-p for sub-talker sampling.

subtalker_temperaturenumberdefault: 0.9

Temperature for sub-talker sampling.

max_new_tokensintegerdefault: 200

Maximum number of new codec tokens to generate.

enable_safety_checkerbooleandefault: true

Authorized callers may set false to request relaxed screening.

More from Qwen 3 TTS

Qwen 3 TTS - Clone Voice [1.7B]

Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!

clone-voicevoice-clone

audio-to-audio

Qwen 3 TTS - Voice Design [1.7B]

Create custom voices using Qwen3-TTS Voice Design model and later use Clone Voice model to create your own voices!

voice-design

text-to-speech

Qwen 3 TTS - Text to Speech [0.6B]

Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model

text-to-speech

Qwen 3 TTS - Clone Voice [0.6B]

Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!

clone-voicevoice-clone

audio-to-audio

Related text to speech models

Eleven v4

Generate expressive speech with Eleven v4 from ElevenLabs. Control delivery with audio tags, voice stability, similarity settings, and IPA pronunciation.

audiovoiceover

text-to-speech

MiniMax Speech 2.8 [HD]

Generate speech from text prompts and different voices using the MiniMax Speech-2.8 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

text-to-speech

Gemini 3.8 Flash TTS

Generate expressive speech with Gemini 3.8 Flash TTS. Choose from 30 voices, direct delivery with style instructions, and create single-speaker narration or two-speaker dialogue.

audiodialogue

text-to-speech

MiniMax Speech-02 HD

Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

speech

text-to-speech

ElevenLabs TTS Turbo v2.5

Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.

audio

text-to-speech

Gemini 3.1 Flash Tts

Newest audio model from Google introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.

lipsyncavatar

text-to-speech

MiniMax Voice Cloning

Clone a voice from a sample audio and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.

speech

text-to-speech

Eleven v4 Turbo

Generate speech with Eleven v4 Turbo from ElevenLabs. Choose a voice and control delivery with audio tags, stability, similarity settings, and IPA pronunciation.

audiovoiceover

text-to-speech

MiniMax Speech 2.6 [HD]

Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

text-to-speech

MiniMax Voice Design

Design a personalized voice from a text description, and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.

speech

text-to-speech

MiniMax Speech 2.8 [Turbo]

Generate speech from text prompts and different voices using the MiniMax Speech-2.8 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.

text-to-speech

✦ new

HeyGen Voice

HeyGen Voice turns text into natural speech with a library voice or an instant clone from a reference clip.

heygentts

text-to-speech