ttsmodels.
53 models indexed

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

AP Paid

Amazon Polly

AWS TTS with 60+ voices and languages.

Cloud Multilingual API
View details
AA Paid

Azure AI Speech

Neural voices with custom and avatar options.

Cloud Multilingual Custom Voice
View details
B Free

Bark

Generative audio model with music and sound effects.

Open-Source Expressive Multilingual
View details
CS Paid

Cartesia Sonic

Ultra-low-latency voices for real-time agents.

Real-Time Low-Latency API
View details
C Free

Chatterbox

A lightweight, fast TTS model built on LLaMA.

Lightweight Open-Source Fast
View details
C Free

ChatTTS

Conversational TTS with detailed prosody control.

Conversational Chinese English
View details
CT Free

Coqui TTS

A batteries-included deep-learning TTS toolkit.

Open-Source Toolkit Multilingual
View details
C Free

CosyVoice

Multilingual zero-shot voice generation from Alibaba.

Open-Source Multilingual Voice Cloning
View details
DA Paid

Deepgram Aura

Fast, natural TTS for conversational AI.

Real-Time API Developer
View details
D Paid

Descript

Powerful editor with built-in TTS.

Editor Voice Clone Podcasting
View details
D Free

Dia

A 1.6B parameter TTS model from Nari Labs.

Open-Source High-Quality Dialogue
View details
E Paid

ElevenLabs

Ultra-realistic voices with emotion and multilingual support.

Voice Cloning Multilingual API
View details
EN Free

eSpeak NG

Lightweight TTS with wide language coverage.

Compact Multi-language Open-Source
View details
F Free

F5-TTS

A fast flow-matching model with fluent voice cloning.

Open-Source Voice Cloning Fast
View details
F Free

Festival

University of Edinburgh's TTS engine.

Academic Multi-language Open-Source
View details
FS Free

Fish Speech v1.2

Trained on 300K hours, supports English, Chinese, Japanese.

Voice Cloning Multilingual Open-Source
View details
F Paid

Fliki

Create videos with TTS and stock media.

Text-to-Video AI Voice Content
View details
GC Paid

Google Cloud TTS

WaveNet and Neural2 voices in 50+ languages.

Cloud Multilingual API
View details
H Paid

HeyGen

AI avatars with expressive voice options.

Video Avatar Voice
View details
HO Paid

Hume Octave

An emotionally intelligent speech-language model.

Expressive Emotion API
View details
I Free

IndexTTS

A controllable zero-shot TTS from Bilibili.

Open-Source Voice Cloning Industrial
View details
K Free

Kokoro

An 82M parameter TTS model by Hexgrad.

Compact Open-Source Efficient
View details
L Paid

Listnr

AI voice generator and podcast host.

Podcast Commercial Voiceover
View details
L Paid

LMNT

Low-latency voices and cloning via API.

Real-Time Voice Cloning API
View details
LG Paid

LOVO (Genny)

AI voiceover and video studio with 500+ voices.

Voiceover Video Studio
View details
M Free

MARS5-TTS

Expressive speech generation with complex prosody.

Dynamic Prosody Open-Source Voice Cloning
View details
M Free

MeloTTS

High-quality multilingual TTS that runs on CPU.

Open-Source Multilingual Real-Time
View details
M Free

MetaVoice-1B

High-quality multilingual speech with emotional nuance.

Multilingual Expressive Open-Source
View details
MT Free

Mozilla TTS

A high-quality TTS engine with multi-language support.

Open-Source Customizable Classic
View details
M Paid

Murf.ai

Simple and powerful voiceovers in 20+ languages.

User-Friendly Voice Library Studio
View details
N Paid

NaturalReader

Long-standing TTS for personal and professional use.

Classic Educational Accessibility
View details
OT Paid

OpenAI TTS

Steerable, natural voices via the OpenAI API.

API Steerable Developer
View details
O Free

OpenVoice

Zero-shot voice cloning across multiple languages.

Voice Cloning Cross-language Open-Source
View details
O Free

Orpheus

Comes in 3B/1B/400M/150M variants by Canopy Labs.

Scalable Flexible Open-Source
View details
O Free

OuteTTS

Pure language-model TTS with cross-lingual cloning.

Open-Source Multilingual LLM-Based
View details
P Free

Parler-TTS

Advanced control over pitch, speed, and emotion.

Customizable Open-Source Prompt-Controlled
View details
P Free

Piper

Fast, local neural TTS optimised for the Raspberry Pi.

Lightweight Open-Source On-Device
View details
P Paid

Play.ht

Large voice library and exportable TTS.

Podcasting Export Options API
View details
RA Paid

Resemble AI

Voice cloning, real-time speech, and deepfake detection.

Voice Cloning Real-Time API
View details
R Paid

Respeecher

Lifelike voice transformation for creative projects.

Creative Voice Cloning Film
View details
RA Paid

Rime AI

Realistic, on-brand voices for production voice agents.

Real-Time API Conversational
View details
SC Free

Sesame CSM

A 1B parameter open-source TTS model from Sesame.

Open-Source Robust Conversational
View details
S Free

Spark-TTS

LLM-based TTS with efficient single-stream tokens.

Open-Source Voice Cloning LLM-Based
View details
S Paid

Speechify

Natural-sounding reading companion.

Mobile Education Accessibility
View details
S2 Free

StyleTTS 2

Human-level synthesis via style diffusion.

Open-Source High-Quality Diffusion
View details
TT Free

Tortoise TTS

Highly realistic, multi-voice synthesis (quality over speed).

Open-Source High-Quality Voice Cloning
View details
T Paid

Typecast

Expressive AI voice actors for stories.

Character Voices Expressive Video
View details
US Paid

Unreal Speech

Low-cost, scalable TTS API for high volume.

API Low-Cost Scalable
View details
V Paid

Voicemaker

Adjust pitch, speed, and effects in TTS.

Customizable Effects Voiceover
View details
WL Paid

WellSaid Labs

Enterprise-grade voice studio and API.

Voice Studio Commercial Enterprise
View details
W Free

WhisperSpeech

An open TTS built by inverting Whisper.

Open-Source Research Multilingual
View details
X Free

XTTS-v2

Multilingual voice cloning with only 6 seconds of audio.

Multilingual Voice Cloning Open-Source
View details
Z Free

Zonos

Expressive 1.6B open model with high-fidelity cloning.

Open-Source Voice Cloning Expressive
View details