Phonon New

Gradium's open-weight text-to-speech, small enough to run offline on phones, laptops, browsers and a Raspberry Pi, with 100+ built-in voices in English, French, German, Spanish and Portuguese. Handy for in-game character voices.

Visit Phonon →

Categories
Voice
Pricing
Free 31m English model is Apache-2.0; 40m and multilingual models are CC BY-NC (commercial use via Gradium sales)
Est. monthly spend
Light Free · Medium Free · Heavy Free (est.)
Open weights, runs locally; commercial use of larger models needs a licence. Rough estimates from vendors' public pricing, checked 28 Oct 2026. Not exact — always check the vendor.
Website
https://gradium.ai/phonon
Added
21 Oct 2026
text to speechon-deviceopen weightsofflinemultilingual

Compare: Best free AI tools for indie devs · Best AI voice generators for game characters and voiceover

Similar tools

Hex

New

Free, open-source local voice dictation for Mac, Windows and Linux from the OpenCode team: hold a shortcut, speak, and it transcribes on-device and pastes into any app, great for dictating prompts to coding agents. Can optionally clean up transcripts through a running OpenCode service. Trending among developers, Nov 2026.

AI Coding Agents & IDEs Voice free

Est. monthly spend: Free · est.

Visit → Details

ElevenLabs

New

Industry-leading AI voice synthesis with realistic speech, voice cloning, and music generation. New in Oct 2026: Eleven Realtime speech-to-speech models (v1 Mini and v1 Max, 90+ languages) for low-latency voice agents and interactive characters, via an OpenAI-compatible Realtime API. New Nov 2 2026: SFX v3 sound effects model in the API (eleven_text_to_sound_v3), which follows multi-part prompts more closely and handles vocals and music better.

Voice freemium

Est. monthly spend: Free–$22/mo · est.

Visit → Details

Fish Audio

New

Expressive text-to-speech and voice cloning with emotion tags, powered by its Drama 3 voice model.

Voice freemium

Est. monthly spend: Free–$15/mo · est.

Visit → Details

Gemini 3.8 Flash TTS

New

Google's expressive text-to-speech model in the Gemini API and AI Studio: 2,000+ library voices, voice design from a text prompt, 30-second voice replication, per-line acting direction and two-speaker scenes in 130 languages. New Nov 4 2026: Voice Remixing lets you tweak any voice's timbre, pitch, pace, accent and delivery with a prompt, handy for NPC and character voices.

Voice freemium

Est. monthly spend: Unknown

Visit → Details