Cyberax AI Playbook
cyberax.com
← All models
Model · OpenAI · Text-To-Speech

OpenAI TTS

OpenAI's general-purpose text-to-speech API. Six preset voices, predictable cost, and tight integration with the rest of the OpenAI stack.

Modality
Text-To-Speech
License
Proprietary (Proprietary)
Released
November 6, 2023
Last verified
May 10, 2026
Runs locally
No

Strengths

  • Predictable, well-priced API
  • Quality good enough for most podcast/voiceover use cases
  • Same API key as the rest of OpenAI

Weaknesses

  • No voice cloning — six preset voices only
  • Closed weights
  • Less expressive than ElevenLabs at the high end

Try it

WhereTypeNotes
OpenAI API hosted-api API key required

Official sources

Change log

  • — Initial entry.
  • — Marked deprecated after verification that GPT-4o mini TTS is OpenAI's current speech generation model.

Related models

ElevenLabs Eleven v4

ElevenLabs · Text-To-Speech

ElevenLabs' flagship expressive TTS (eleven_v4), with eleven_v4_turbo as its real-time variant (~100ms median inference). The benchmark for natural-sounding speech and voice cloning across 90+ languages.

Proprietary
Try on: ElevenLabs API · ElevenLabs Studio
Released Sep 2026 · Verified 2026-10-28

Chatterbox

Resemble AI · Text-To-Speech

Resemble AI's MIT-licensed open text-to-speech family. Multilingual V3 (500M) clones a voice in 23 languages; Turbo (350M) and Nano (110M) are English-only models for fast voice agents, with [laugh]-style tags. Every output is watermarked.

MIT Open Runs locally Mac · 8 GB+
Try on: Hugging Face · GitHub (chatterbox-tts package) · Resemble AI
Released Jun 2026 · Verified 2026-10-28

VoxCPM2

OpenBMB · Text-To-Speech

OpenBMB's open text-to-speech model — 30 languages, voice cloning from a short clip, and Voice Design that invents a new voice from a written description. Apache 2.0, so a business can ship it without a licence fee.

Apache 2.0 Open Runs locally Mac (slow) · 16 GB+
Try on: Hugging Face · GitHub (voxcpm package)
Released Apr 2026 · Verified 2026-10-28

Qwen3-TTS

Alibaba · Text-To-Speech

Alibaba's open text-to-speech family. The headline 1.7B CustomVoice model speaks 10 languages in nine preset voices you can steer with plain-language instructions; sibling models clone a voice from 3 seconds of audio or design one from a description.

Apache 2.0 Open Runs locally Mac · 8 GB+
Try on: Hugging Face · GitHub (qwen-tts package) · Alibaba Cloud Model Studio (DashScope)
Released Jan 2026 · Verified 2026-10-28

Kokoro-82M

hexgrad · Text-To-Speech

A tiny open text-to-speech model (82 million parameters) with 54 preset voices in 8 languages. Quality close to much larger models at a fraction of the cost — the most-downloaded TTS model on Hugging Face.

Apache 2.0 Open Runs locally Mac · 8 GB+
Try on: Hugging Face · GitHub (kokoro package)
Released Jan 2025 · Verified 2026-10-28

Piper

Rhasspy · Text-To-Speech

A fast, local TTS designed for Raspberry Pi-class hardware. Powers most self-hosted voice assistants where Whisper handles input and Piper handles output. Now maintained by the Open Home Foundation under GPL-3.0.

GPL-3.0 Open weights Runs locally Mac · 8 GB+
Try on: GitHub · Hugging Face voices
Released Apr 2023 · Verified 2026-10-28