Coqui XTTS v2
Multilingual text-to-speech with voice cloning. It's for people making images, video, or audio. It's free.
Get patch notes
Same daily newsletter as the rest of the site. One email a day.
No affiliate link on file. Outbound goes to huggingface.co. Identity checked October 21, 2026. Score null is from the run on October 21, 2026.
Grade
We tried it ourselves. Grade C.
- Grade
- C · We tried it
- Score
- 6/10
- Price
- Free
Best for
Jobs people use this for.
Test details
Multilingual text-to-speech with zero-shot voice cloning. Code is MPL-2.0 (idiap/coqui-ai-TTS). Weights are the Coqui Public Model License, non-commercial.
Hands-on review · 2026-10-21
TestedC6/10- CPU-only box: 8 cores, 15 GB RAM (about 4-10 GB free during tests), no GPU.
- No listening or speaker-similarity test
- Clone run shared the CPU with an npm install
- Weights are Coqui Public Model License, non-commercial.
XTTS v2 spoke our script almost perfectly and cloned a voice from a 13-second clip without any training. On a CPU it is slow, taking more than two minutes for 15 seconds of speech, and the first run crashed until we added a missing audio package. The model licence forbids commercial use. We didn't listen to the clips or measure how close the clone sounds, only how clearly it speaks.
Accurate speech and easy voice cloning, but slow on CPU and non-commercial.
- Coverage
- Built-in voice plus one clone. Intelligibility from whisper.cpp. No listening test.
- What we tested
- The site's TTS script with a built-in voice, plus voice cloning from a 12.8 s reference clip (our Kokoro output). We scored intelligibility by transcribing each clip with whisper.cpp.
Method
coqui-tts 0.28.0 (the maintained idiap fork) with torch 2.14 CPU, tts_models/multilingual/multi-dataset/xtts_v2, COQUI_TOS_AGREED=1. The first run crashed until we added the `codec` extra (torchcodec). WER from whisper.cpp base.en (_battery/wer.sh).
Measured
- download_and_load_s29.8
- builtin_voice140.1 s for 15.2 s of audio (9.2x slower than real time). WER 0.030 ('AgentTested' heard as 'Agentested')
- voice_clone191.9 s for 13.2 s (14.6x slower; an npm install was running at the same time). WER 0.061
- peak_rssabout 4.5 GB
- listening_testnone
Pros
- Very intelligible: WER 0.03-0.06, as good as Piper and Kokoro
- Clones a voice from one short clip, with no training
- Supports many languages
Cons
- About 9-15x slower than real time on CPU
- Needed an extra package fix (torchcodec) before it ran
- Model licence (CPML) is non-commercial only
- Uses about 4.5 GB of RAM
- Status
- Not run
- Date
- October 21, 2026
- Time to first output
- —
- Cost
- —
- Result
- —
- Evidence
- Log linked below
Queued task. Render a fixed script in a chosen voice. Log time to the first usable take and artifacts.
FAQ
What is the agent-tested verdict for Coqui XTTS v2?
Multilingual text-to-speech with voice cloning. It's for people making images, video, or audio. It's free. We tried it ourselves. Grade C.
How much does Coqui XTTS v2 cost?
Free. Free (non-commercial model licence)
Do sponsors outrank this tool?
No. A sponsored slot is labeled and sold separately from tiers. It cannot move this listing.