Text to Speech Models

Chatterbox TTS

Fal.ai

Text-to-speech for memes, videos, games, and AI agents.

ElevenLabs Flash V2.5

ElevenLabs

Fastest ElevenLabs model for ultra-low latency text-to-speech.

ElevenLabs Multilingual V2

ElevenLabs

High-quality multilingual text-to-speech supporting 29 languages with emotional range.

ElevenLabs Turbo V2.5

ElevenLabs

Fast text-to-speech optimized for low latency with good quality.

ElevenLabs V3

ElevenLabs

Latest ElevenLabs model with best-in-class voice quality and expressiveness.

Kokoro 82M

Jaaari (via Replicate)

Lightweight 82M parameter text-to-speech model with natural voices.

Maya TTS

Fal.ai

State-of-the-art speech model for expressive voice generation.

Expressive voice generation

OpenVoice

MyShell (via Replicate)

Instant voice cloning with fine-grained control over style, emotion, and accent.

Parler TTS

Replicate

Describe the voice you want in text. Generate speech matching your description.

Speech 02 HD

MiniMax (via Replicate)

High-definition text-to-speech with premium voice quality.

Speech 02 Turbo

MiniMax (via Replicate)

Fast text-to-speech variant of Speech 02 optimized for speed.

XTTS-v2

Coqui (via Replicate)

Clone any voice with just 6 seconds of audio. Supports 17 languages.

Clone voices in seconds