Voice Synthesis Models

Chatterbox TTS is a zero-shot text-to-speech model that generates expressive speech by cloning voices from reference audio while allowing emotional intensity and speech pattern adjustments.

Transform your PDFs into engaging AI podcasts with NVIDIA PDF to Podcast. Convert documents to audio, customize voices, and set durations for rich, on-the-go content.

Get Piper Persian Text-to-Speech for efficient, local speech synthesis. Optimized for Raspberry Pi, it converts Persian text to audio, ideal for voice assistants and accessibility.

Minimax Voice Cloning is a model that creates custom voice clones from short audio samples for integration with Minimax's text-to-speech systems, requiring only 5 seconds of audio for training.

Minimax Speech-02 Turbo is a real-time text-to-audio model with voice cloning, emotional expression controls, and multilingual support.

Minimax Speech-02-HD is a text-to-speech model that generates natural audio output with control over vocal characteristics like emotion, language, pitch, and speed for professional applications.

Kimi Audio 7B Instruct is a multimodal audio model that performs speech-to-text, text-to-speech, audio reasoning, captioning, and emotion recognition through acoustic feature extraction and parallel text/audio generation.

PrunaAI Dia 1.6B revolutionizes expressive voice generation with multi-speaker dialogue and non-verbal cues. Create dynamic, natural-sounding audio for diverse applications.

Dia 1.6B generates realistic dialogue audio from text with speaker tags and non-verbal cues, optionally cloning voices from an audio prompt.

DeepAudio-V1 Model generates synchronized audio and speech outputs from video inputs using multi-stage processing, including configurable generation steps and prompts.

Cog Orpheus 3B is a multilingual text-to-speech model generating expressive speech with emotional tags and voice cloning capabilities.

Review F5-TTS Vietnamese for text-to-speech and reference-audio voice cloning, including text inputs, reference-text settings, speed controls and examples.

Spark TTS converts text into speech through voice cloning (using audio prompts) or voice creation (with customizable gender, pitch, and speed parameters) while controlling generation randomness.

Review MOSS-TTS v1.5 model details: OpenMOSS model ID, voice cloning, long-form TTS, multilingual synthesis, Pinyin/IPA control, pause control, and local runtime caveats.

Hurston-1 generates accented English at 24 kHz or phone-mode 8 kHz G.711, with gated Apache-2.0-labelled weights and no verified hosted API price.