Nari Labs Qwen3-TTS and Qwen3-ASR: low latency speech APIs
Nari Labs serves Qwen3-TTS and Qwen3-ASR as fast speech APIs, $5 per million characters and $0.06 per audio hour, plus an Apache-2.0 TTS server for one H100.
Tag
4 posts tagged #tts
Browse 4 posts tagged Tts. Setup notes, reviews, comparisons, and workflow patterns.
Nari Labs serves Qwen3-TTS and Qwen3-ASR as fast speech APIs, $5 per million characters and $0.06 per audio hour, plus an Apache-2.0 TTS server for one H100.
VoxCPM is a tokenizer-free text-to-speech model from OpenBMB that handles multilingual synthesis, creative voice design, and zero-shot voice cloning in a single architecture. Apache 2.0.
VoiceStudio is a fully-local, open-source alternative to ElevenLabs: voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation across 646 languages. AGPL-3.0.
TTSLab runs text-to-speech and speech-to-text models entirely in your browser via WebGPU. No server, no API keys, no data sent anywhere.