{"data":{"id":"deepinfra/Qwen/Qwen3-TTS","provider_id":"deepinfra","name":"Qwen/Qwen3-TTS","modalities":["audio"],"context_window":null,"family":"Qwen3-TTS","status":"active","description":"Qwen3-TTS is an advanced text-to-speech model by Alibaba's Qwen team, delivering stable, expressive, and low-latency speech generation across 10 languages. Key capabilities: - 9 preset voices — Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee — covering diverse genders, ages, and accents - Voice cloning — clone any voice from a short (~3s) audio sample via the voice_id parameter - Instruction control — adjust tone, emotion, and speaking style with natural language (e.g. \"speak slowly and calmly\", \"excited tone\") - 10 languages — English, Chinese, Japanese, Korean, German, French, Russian, Spanish, Italian, Portuguese - Streaming support — real-time PCM streaming with ~97ms first-byte latency - Multiple output formats — WAV, MP3, FLAC, PCM Built on a 1.7B parameter architecture using discrete multi-codebook language modeling for end-to-end speech synthesis without cascading errors. Uses a custom 12Hz acoustic tokenizer that preserves paralinguistic information and environmental audio details.","architecture":null,"supported_parameters":["tts"],"created_at":null,"canonical_slug":"Qwen/Qwen3-TTS","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"alibaba","creator_name":"Alibaba","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":20,"savings_pct":null,"savings_basis":null,"provider":{"id":"deepinfra","name":"DeepInfra","website":"https://deepinfra.com","categories":["text","image","audio","video"],"docs_url":"https://deepinfra.com/pricing","notes":"Secondary live feed from DeepInfra's public models API. Prices are DeepInfra's rates, not the origin lab's. Does not block the OpenRouter sync.","role":"host"},"prices":[{"id":60308,"model_id":"deepinfra/Qwen/Qwen3-TTS","unit":"character","input_per_1m_usd":20,"output_per_1m_usd":null,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/Qwen/Qwen3-TTS","notes":"DeepInfra public models API. Token and character rates are already USD per 1M. Per-image and per-second rates are stored as flat USD. Discount, when present, is not applied. input_characters is USD per 1M characters.","last_verified_at":"2026-10-08T17:11:32.756Z","source":"deepinfra","confidence":"official","cache_read_per_1m_usd":null,"cache_write_per_1m_usd":null,"cache_write_1h_per_1m_usd":null,"pricing_detail":null,"long_context_override":false}]}}