Every text-to-speech model, in one place.
A hand-curated directory of the best open-source and commercial TTS engines. Search by name, capability, or use case.
All models
53 results
Amazon Polly
AWS TTS with 60+ voices and languages.
Azure AI Speech
Neural voices with custom and avatar options.
Bark
Generative audio model with music and sound effects.
Cartesia Sonic
Ultra-low-latency voices for real-time agents.
Chatterbox
A lightweight, fast TTS model built on LLaMA.
ChatTTS
Conversational TTS with detailed prosody control.
Coqui TTS
A batteries-included deep-learning TTS toolkit.
CosyVoice
Multilingual zero-shot voice generation from Alibaba.
Deepgram Aura
Fast, natural TTS for conversational AI.
Descript
Powerful editor with built-in TTS.
Dia
A 1.6B parameter TTS model from Nari Labs.
ElevenLabs
Ultra-realistic voices with emotion and multilingual support.
eSpeak NG
Lightweight TTS with wide language coverage.
F5-TTS
A fast flow-matching model with fluent voice cloning.
Festival
University of Edinburgh's TTS engine.
Fish Speech v1.2
Trained on 300K hours, supports English, Chinese, Japanese.
Fliki
Create videos with TTS and stock media.
Google Cloud TTS
WaveNet and Neural2 voices in 50+ languages.
HeyGen
AI avatars with expressive voice options.
Hume Octave
An emotionally intelligent speech-language model.
IndexTTS
A controllable zero-shot TTS from Bilibili.
Kokoro
An 82M parameter TTS model by Hexgrad.
Listnr
AI voice generator and podcast host.
LMNT
Low-latency voices and cloning via API.
LOVO (Genny)
AI voiceover and video studio with 500+ voices.
MARS5-TTS
Expressive speech generation with complex prosody.
MeloTTS
High-quality multilingual TTS that runs on CPU.
MetaVoice-1B
High-quality multilingual speech with emotional nuance.
Mozilla TTS
A high-quality TTS engine with multi-language support.
Murf.ai
Simple and powerful voiceovers in 20+ languages.
NaturalReader
Long-standing TTS for personal and professional use.
OpenAI TTS
Steerable, natural voices via the OpenAI API.
OpenVoice
Zero-shot voice cloning across multiple languages.
Orpheus
Comes in 3B/1B/400M/150M variants by Canopy Labs.
OuteTTS
Pure language-model TTS with cross-lingual cloning.
Parler-TTS
Advanced control over pitch, speed, and emotion.
Piper
Fast, local neural TTS optimised for the Raspberry Pi.
Play.ht
Large voice library and exportable TTS.
Resemble AI
Voice cloning, real-time speech, and deepfake detection.
Respeecher
Lifelike voice transformation for creative projects.
Rime AI
Realistic, on-brand voices for production voice agents.
Sesame CSM
A 1B parameter open-source TTS model from Sesame.
Spark-TTS
LLM-based TTS with efficient single-stream tokens.
Speechify
Natural-sounding reading companion.
StyleTTS 2
Human-level synthesis via style diffusion.
Tortoise TTS
Highly realistic, multi-voice synthesis (quality over speed).
Typecast
Expressive AI voice actors for stories.
Unreal Speech
Low-cost, scalable TTS API for high volume.
Voicemaker
Adjust pitch, speed, and effects in TTS.
WellSaid Labs
Enterprise-grade voice studio and API.
WhisperSpeech
An open TTS built by inverting Whisper.
XTTS-v2
Multilingual voice cloning with only 6 seconds of audio.
Zonos
Expressive 1.6B open model with high-fidelity cloning.
No models found
Try a different search term or filter.