{"version":"1","model":{"id":"fal-ai/qwen-3-tts/voice-design/1.7b","name":"Qwen 3 TTS Voice Design (1.7B)","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"Design a custom voice from a text description and synthesize speech in that voice using Qwen 3 TTS.","pricing_note":"$0.09 / 1k chars (fal-published)","categories":["narrate"],"prompt_required":true,"prompt_supported":true,"supports":{},"aspect_ratios":[],"resolutions":[],"durations":[],"base_credits":1,"api_gross_margin_percent":20,"added_at":"2026-05-19","popularity_rank":45,"example_prompt":"Voice: warm middle-aged woman with a soft British accent, gentle pacing, slightly raspy. Script: 'Welcome back. Let's pick up where we left off.'","preview":{"image":"/images/model-previews/generated/qwen-3-voice-design-v1.webp"},"schema_url":"/api/v1/models?id=fal-ai%2Fqwen-3-tts%2Fvoice-design%2F1.7b","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fqwen-3-tts%2Fvoice-design%2F1.7b","title":"Qwen 3 TTS Voice Design (1.7B) generation request","description":"Request body accepted by POST /api/v1/generate for fal-ai/qwen-3-tts/voice-design/1.7b.","type":"object","properties":{"model_id":{"type":"string","const":"fal-ai/qwen-3-tts/voice-design/1.7b","description":"ArtEmotion model identifier."},"extra":{"type":"object","additionalProperties":true,"description":"Model-specific settings may also be nested here."},"max_credits":{"type":"number","minimum":1,"description":"Reject before submission if the estimated list price exceeds this cap."},"webhook_url":{"type":"string","format":"uri","maxLength":2048},"webhook_secret":{"type":"string","maxLength":512},"folder_id":{"type":"string"},"prompt":{"type":"string"},"voice_style":{"title":"Voice Style","description":"Describe the voice characteristics — tone, accent, emotion, pace. e.g. 'Warm middle-aged woman, soft British accent, gentle pace'.","default":"","type":"string"},"language":{"title":"Language","description":"The language of the voice to be designed.","default":"Auto","type":"string","enum":["Auto","English","Chinese","Spanish","French","German","Italian","Japanese","Korean","Portuguese","Russian"]},"temperature":{"title":"Temperature","description":"Speech randomness. Lower = more consistent, higher = more varied.","default":0.9,"type":"number","minimum":0,"maximum":1,"multipleOf":0.05},"repetition_penalty":{"title":"Repetition Penalty","description":"Penalizes repeated sounds or audio patterns.","default":1.05,"type":"number","minimum":0,"maximum":2,"multipleOf":0.05},"top_p":{"title":"Top P","description":"Top-p sampling parameter.","default":1,"type":"number","minimum":0,"maximum":1,"multipleOf":0.05},"top_k":{"title":"Top K","description":"Top-k sampling parameter.","default":50,"type":"number","minimum":0,"maximum":200,"multipleOf":1},"max_new_tokens":{"title":"Max New Tokens","description":"Maximum number of new codec tokens to generate.","default":200,"type":"number","minimum":1,"maximum":8192,"multipleOf":1},"subtalker_dosample":{"title":"Subtalker Dosample","description":"Sampling switch for the sub-talker.","default":true,"type":"boolean"},"subtalker_temperature":{"title":"Subtalker Temperature","description":"Temperature for sub-talker sampling.","default":0.9,"type":"number","minimum":0,"maximum":1},"subtalker_top_k":{"title":"Subtalker Top K","description":"Top-k for sub-talker sampling.","default":50,"type":"number","minimum":0,"multipleOf":1},"subtalker_top_p":{"title":"Subtalker Top P","description":"Top-p for sub-talker sampling.","default":1,"type":"number","minimum":0,"maximum":1}},"required":["model_id","prompt"],"additionalProperties":false},"parameters":[{"key":"voice_style","label":"Voice Style","type":"text","default":"","description":"Describe the voice characteristics — tone, accent, emotion, pace. e.g. 'Warm middle-aged woman, soft British accent, gentle pace'."},{"key":"language","label":"Language","type":"select","default":"Auto","options":["Auto","English","Chinese","Spanish","French","German","Italian","Japanese","Korean","Portuguese","Russian"],"description":"The language of the voice to be designed."},{"key":"temperature","label":"Temperature","type":"number","default":0.9,"min":0,"max":1,"step":0.05,"description":"Speech randomness. Lower = more consistent, higher = more varied."},{"key":"repetition_penalty","label":"Repetition Penalty","type":"number","default":1.05,"min":0,"max":2,"step":0.05,"description":"Penalizes repeated sounds or audio patterns."},{"key":"top_p","label":"Top P","type":"number","default":1,"min":0,"max":1,"step":0.05,"description":"Top-p sampling parameter."},{"key":"top_k","label":"Top K","type":"number","default":50,"min":0,"max":200,"step":1,"description":"Top-k sampling parameter."},{"key":"max_new_tokens","label":"Max New Tokens","type":"number","default":200,"min":1,"max":8192,"step":1,"description":"Maximum number of new codec tokens to generate."},{"key":"subtalker_dosample","label":"Subtalker Dosample","type":"toggle","default":true,"description":"Sampling switch for the sub-talker."},{"key":"subtalker_temperature","label":"Subtalker Temperature","type":"number","default":0.9,"min":0,"max":1,"description":"Temperature for sub-talker sampling."},{"key":"subtalker_top_k","label":"Subtalker Top K","type":"number","default":50,"min":0,"step":1,"description":"Top-k for sub-talker sampling."},{"key":"subtalker_top_p","label":"Subtalker Top P","type":"number","default":1,"min":0,"max":1,"description":"Top-p for sub-talker sampling."}]}}