Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
Log in

Best Text to Speech (TTS) Models - Independent Comparison

Compare quality, speed, and price to find the best speech generation models in 2025 for voice agents, creative media, knowledge sharing, and assistants.

For further details, see our methodology page.

Quality

Text to Speech Arena Quality ELO

Arena ELO: Average ELO rating of the model, Higher is better

Relative ELO score of the models as determined by responses from users in Artificial Analysis' Speech Arena. Some models may not be shown due to not yet having enough votes.

Pricing

Price

Price: USD per 1M characters of text, Lower is better

Price per 1M characters of text. For detail on how we calculate price for providers which price based on inference time or subscription plans, see our methodology page.

Speed Factor

Characters Per Second

Characters processed per second: # of characters per second of generation time, Higher is better

Number of characters processed per second of generation time. Higher values indicate faster generation speeds.

Text to Speech models & providers compared

Async Flash v1.0, Azure Neural, Chatterbox, Chatterbox HD, Chirp 3: HD, Eleven v3, ElevenLabs v3 - Alpha, Falcon (Beta), Fish Speech 1.5, Flash v2.5, Gemini 2.5 Flash TTS (Dec 2025), Gemini 2.5 Flash Lite TTS, Gemini 2.5 Flash TTS, Gemini 2.5 Pro TTS, Inworld TTS 1, Inworld TTS 1 Max, Journey, Kokoro 82M v1.0, LMNT, Magpie Multilingual, Magpie-Multilingual 357M, Maya1, MetaVoice v1, Multilingual v2, Murf Speech Gen 2, Neural2, Octave 2, Octave TTS, OpenAudio S1, OpenVoice v2, Polly Generative, Polly Long-Form, Polly Neural, Polly Standard, Qwen3 TTS Flash, Qwen3 TTS, SIMBA 1.0, Sonic 3, Sonic English (Oct '24), Speech 2.6 HD, Speech 2.6 Turbo, Speech-02-HD, Speech-02-Turbo, Standard, Step Audio EditX, Step TTS 2, Step TTS Mini, Studio, StyleTTS 2, T2A-01-HD, T2A-01-Turbo, TTS-1, TTS-1 HD, Inworld TTS 1.5 Max, Inworld TTS 1.5 Mini, Turbo v2.5, VibeVoice 1.5B, VibeVoice 7B, WaveNet, XTTS v2, Zonos-v0.1, xAI Text to Speech (Beta).