kokoro · hook
Generated locally with Kokoro-82M v1.0 (int8 ONNX), voice af_heart.
License: Apache-2.0 (model); sample generated for Text2Voice · source
Tape log
Licenses & credits
Text2Voice does not generate live speech through commercial APIs. Every playable file is either synthesized here from open models, or copied from a public vendor/paper demo and labelled as such.
Shared bench scripts (hook, narration, dialogue, news, numbers) were written for this site. They were rendered locally with eSpeak NG, Festival (kal diphone), Flite (slt), Piper (en_US-lessac-medium), Kokoro-82M (af_heart, int8 ONNX), Kyutai Pocket TTS (alba), and Meta MMS-TTS English (facebook/mms-tts-eng). Those seven engines are the fair comparison set.
Vendor and paper clips remain the property of their publishers. They are archived here for criticism, research, and comparison, with source URLs on every record. If you own a clip and want it removed, replace the file with silence and keep the catalog row — do not invent a substitute.
Do not treat a vendor demo as our bench line. The interface flags those clips in oxide red. Transcripts for documentation samples follow the publisher’s page where the sentence is printed; otherwise the caption says so.
Clip register
kokoro · narration
Generated locally with Kokoro-82M v1.0 (int8 ONNX), voice af_heart.
License: Apache-2.0 (model); sample generated for Text2Voice · source
kokoro · dialogue
Generated locally with Kokoro-82M v1.0 (int8 ONNX), voice af_heart.
License: Apache-2.0 (model); sample generated for Text2Voice · source
kokoro · news
Generated locally with Kokoro-82M v1.0 (int8 ONNX), voice af_heart.
License: Apache-2.0 (model); sample generated for Text2Voice · source
kokoro · numbers
Generated locally with Kokoro-82M v1.0 (int8 ONNX), voice af_heart.
License: Apache-2.0 (model); sample generated for Text2Voice · source
piper · hook
Generated locally with Piper, voice en_US-lessac-medium.
License: MIT / GPL-3.0 (Piper); sample generated for Text2Voice · source
piper · narration
Generated locally with Piper, voice en_US-lessac-medium.
License: MIT / GPL-3.0 (Piper); sample generated for Text2Voice · source
piper · dialogue
Generated locally with Piper, voice en_US-lessac-medium.
License: MIT / GPL-3.0 (Piper); sample generated for Text2Voice · source
piper · news
Generated locally with Piper, voice en_US-lessac-medium.
License: MIT / GPL-3.0 (Piper); sample generated for Text2Voice · source
piper · numbers
Generated locally with Piper, voice en_US-lessac-medium.
License: MIT / GPL-3.0 (Piper); sample generated for Text2Voice · source
espeak-ng · hook
Generated locally with eSpeak NG 1.51, voice en-us.
License: GPL-3.0; sample generated for Text2Voice · source
espeak-ng · narration
/samples/espeak-ng/narration.mp3
Generated locally with eSpeak NG 1.51, voice en-us.
License: GPL-3.0; sample generated for Text2Voice · source
espeak-ng · dialogue
/samples/espeak-ng/dialogue.mp3
Generated locally with eSpeak NG 1.51, voice en-us.
License: GPL-3.0; sample generated for Text2Voice · source
espeak-ng · news
Generated locally with eSpeak NG 1.51, voice en-us.
License: GPL-3.0; sample generated for Text2Voice · source
espeak-ng · numbers
/samples/espeak-ng/numbers.mp3
Generated locally with eSpeak NG 1.51, voice en-us.
License: GPL-3.0; sample generated for Text2Voice · source
festival · hook
Generated locally with Festival text2wave, kal diphone voice.
License: MIT-style Festival license; sample generated for Text2Voice · source
festival · narration
/samples/festival/narration.mp3
Generated locally with Festival text2wave, kal diphone voice.
License: MIT-style Festival license; sample generated for Text2Voice · source
festival · dialogue
/samples/festival/dialogue.mp3
Generated locally with Festival text2wave, kal diphone voice.
License: MIT-style Festival license; sample generated for Text2Voice · source
festival · news
Generated locally with Festival text2wave, kal diphone voice.
License: MIT-style Festival license; sample generated for Text2Voice · source
festival · numbers
Generated locally with Festival text2wave, kal diphone voice.
License: MIT-style Festival license; sample generated for Text2Voice · source
flite · hook
Generated locally with Flite, slt diphone voice.
License: BSD-like Flite license; sample generated for Text2Voice · source
flite · narration
Generated locally with Flite, slt diphone voice.
License: BSD-like Flite license; sample generated for Text2Voice · source
flite · dialogue
Generated locally with Flite, slt diphone voice.
License: BSD-like Flite license; sample generated for Text2Voice · source
flite · news
Generated locally with Flite, slt diphone voice.
License: BSD-like Flite license; sample generated for Text2Voice · source
flite · numbers
Generated locally with Flite, slt diphone voice.
License: BSD-like Flite license; sample generated for Text2Voice · source
kokoro · demo
/samples/kokoro/vendor-hearme.mp3
Official Kokoro-82M HEARME sample, hexgrad, Hugging Face.
License: Apache-2.0 · source
kokoro · demo
/samples/kokoro/vendor-neuromancer.mp3
Official Kokoro-82M sample af_heart_0 (Gibson line used as test text).
License: Apache-2.0 · source
elevenlabs · demo
/samples/elevenlabs/vendor-home-1.mp3
Official public marketing audio from elevenlabs.io (eleven-public-cdn).
License: Vendor demo · all rights remain with ElevenLabs · source
elevenlabs · demo
/samples/elevenlabs/vendor-narration.mp3
Official public demo audio from elevenlabs.io/text-to-speech.
License: Vendor demo · all rights remain with ElevenLabs · source
openai-tts · demo
/samples/openai-tts/vendor-alloy.mp3
OpenAI API docs voice sample, Alloy.
License: Vendor documentation sample · OpenAI · source
openai-tts · demo
/samples/openai-tts/vendor-nova.mp3
OpenAI API docs voice sample, Nova.
License: Vendor documentation sample · OpenAI · source
openai-4o-audio · demo
/samples/openai-4o-audio/vendor-sky-story.mp3
Official Sky story demo from OpenAI’s 2023 voice announcement CDN.
License: Vendor announcement sample · OpenAI · source
openai-4o-audio · demo
/samples/openai-4o-audio/vendor-sky-info.mp3
Official Sky info demo from OpenAI’s 2023 voice announcement CDN.
License: Vendor announcement sample · OpenAI · source
google-neural2 · demo
/samples/google-neural2/vendor-neural2-a.mp3
Google Cloud TTS docs, en-US-Neural2-A.
License: Vendor documentation sample · Google Cloud · source
google-chirp3 · demo
/samples/google-chirp3/vendor-chirp3-kore.mp3
Google Cloud TTS docs, en-US-Chirp3-HD-Kore.
License: Vendor documentation sample · Google Cloud · source
google-wavenet · demo
/samples/google-wavenet/vendor-wavenet-f.mp3
Google Cloud TTS docs, en-US-Wavenet-F.
License: Vendor documentation sample · Google Cloud · source
google-standard · demo
/samples/google-standard/vendor-standard-b.mp3
Google Cloud TTS docs, en-US-Standard-B.
License: Vendor documentation sample · Google Cloud · source
google-studio · demo
/samples/google-studio/vendor-studio-o.mp3
Google Cloud TTS docs, en-US-Studio-O.
License: Vendor documentation sample · Google Cloud · source
styletts2 · demo
/samples/styletts2/vendor-ljspeech.mp3
StyleTTS 2 official demo page, LJSpeech ID 00005. Same sentence as VITS and NaturalSpeech on that page.
License: Paper demo · see StyleTTS 2 GitHub · source
vits · demo
/samples/vits/vendor-ljspeech.mp3
VITS sample hosted on the StyleTTS 2 demo page, LJSpeech ID 00005.
License: Paper demo · source
vits · demo
/samples/vits/vendor-official.mp3
Official VITS demo, single-speaker LJSpeech, ss_01_vits.wav.
License: Paper demo · source
naturalspeech · demo
/samples/naturalspeech/vendor-ljspeech.mp3
NaturalSpeech sample hosted on the StyleTTS 2 demo page, LJSpeech ID 00005.
License: Paper demo · source
naturalspeech · demo
/samples/naturalspeech-official/vendor-demo.mp3
Official NaturalSpeech demo, sample 0.
License: Paper demo · source
tacotron · demo
/samples/tacotron/vendor-demo.mp3
Tacotron official demo, gan_or_vae_r2.wav. Same sentence as the Tacotron 2 clip.
License: Paper demo · source
tacotron2 · demo
/samples/tacotron2/vendor-demo.mp3
Tacotron 2 official demo, gan_or_vae.wav.
License: Paper demo · source
tacotron2 · demo
/samples/tacotron2/vendor-fastspeech-cmp.mp3
Tacotron 2 baseline from the FastSpeech demo page, sample 1.
License: Paper demo · source
fastspeech · demo
/samples/fastspeech/vendor-demo.mp3
FastSpeech official demo, sample 1. Same sentence as Merlin and Tacotron 2 on that page.
License: Paper demo · source
merlin-hts · demo
/samples/merlin-hts/vendor-demo.mp3
Merlin baseline from the FastSpeech demo page, sample 1.
License: Paper demo · source
fastspeech2 · demo
/samples/fastspeech2/vendor-demo.mp3
FastSpeech 2 official demo, sample 0000000004.
License: Paper demo · source
f5-tts · demo
/samples/f5-tts/vendor-zeroshot.mp3
F5-TTS official demo, Seed-TTS English zero-shot (same-language generation).
License: Paper demo · source
f5-tts · demo
/samples/f5-tts/vendor-speaker1.mp3
F5-TTS clip from the IndexTTS comparison table, Speaker 1.
License: Paper demo · source
matcha-tts · demo
/samples/matcha-tts/vendor-demo.mp3
Matcha-TTS official demo, stimuli/sample_from_test/MAT-10_1.wav.
License: Paper demo · source
indextts · demo
/samples/indextts/vendor-speaker1.mp3
IndexTTS official demo, Speaker 1. Same sentence as XTTS, CosyVoice 2, F5-TTS, Fish Speech.
License: Paper demo · source
xtts-v2 · demo
/samples/xtts-v2/vendor-speaker1.mp3
XTTS v2 clip from the IndexTTS comparison table, Speaker 1.
License: Paper demo · XTTS is CPML (non-commercial) · source
cosyvoice2 · demo
/samples/cosyvoice2/vendor-speaker1.mp3
CosyVoice 2 clip from the IndexTTS comparison table, Speaker 1.
License: Paper demo · source
fish-audio · demo
/samples/fish-speech/vendor-speaker1.mp3
Fish-Speech clip from the IndexTTS comparison table, Speaker 1.
License: Paper demo · Fish Speech research license may apply · source
chatterbox · demo
/samples/chatterbox/vendor-ivr.mp3
Official Chatterbox Turbo demo, IVR / order-number sample.
License: MIT model · demo audio from Resemble · source
spark-tts · demo
/samples/spark-tts/vendor-zeroshot.mp3
Spark-TTS official demo, audios/zero-shot/seedtts-01/seedtts-01_en.wav.
License: Paper demo · source
valle · demo
/samples/valle/vendor-billg.mp3
VALL-E official demo page, audios/bgreview/billg_valle.wav.
License: Paper demo · Microsoft · source
kyutai-pocket-tts · hook
/samples/kyutai-pocket-tts/hook.mp3
Generated locally with Kyutai Pocket TTS, official alba voice prompt.
License: MIT (Pocket TTS); sample generated for Text2Voice · source
kyutai-pocket-tts · narration
/samples/kyutai-pocket-tts/narration.mp3
Generated locally with Kyutai Pocket TTS, official alba voice prompt.
License: MIT (Pocket TTS); sample generated for Text2Voice · source
kyutai-pocket-tts · dialogue
/samples/kyutai-pocket-tts/dialogue.mp3
Generated locally with Kyutai Pocket TTS, official alba voice prompt.
License: MIT (Pocket TTS); sample generated for Text2Voice · source
kyutai-pocket-tts · news
/samples/kyutai-pocket-tts/news.mp3
Generated locally with Kyutai Pocket TTS, official alba voice prompt.
License: MIT (Pocket TTS); sample generated for Text2Voice · source
kyutai-pocket-tts · numbers
/samples/kyutai-pocket-tts/numbers.mp3
Generated locally with Kyutai Pocket TTS, official alba voice prompt.
License: MIT (Pocket TTS); sample generated for Text2Voice · source
meta-mms · hook
Generated locally with Meta MMS-TTS English (facebook/mms-tts-eng, VITS).
License: CC-BY-NC 4.0 (MMS weights); sample generated for Text2Voice · source
meta-mms · narration
/samples/meta-mms/narration.mp3
Generated locally with Meta MMS-TTS English (facebook/mms-tts-eng, VITS).
License: CC-BY-NC 4.0 (MMS weights); sample generated for Text2Voice · source
meta-mms · dialogue
/samples/meta-mms/dialogue.mp3
Generated locally with Meta MMS-TTS English (facebook/mms-tts-eng, VITS).
License: CC-BY-NC 4.0 (MMS weights); sample generated for Text2Voice · source
meta-mms · news
Generated locally with Meta MMS-TTS English (facebook/mms-tts-eng, VITS).
License: CC-BY-NC 4.0 (MMS weights); sample generated for Text2Voice · source
meta-mms · numbers
Generated locally with Meta MMS-TTS English (facebook/mms-tts-eng, VITS).
License: CC-BY-NC 4.0 (MMS weights); sample generated for Text2Voice · source
vibevoice · demo
/samples/vibevoice/vendor-2p-argument.mp3
Official VibeVoice project-page 2-speaker demo (2p_argument.mp3) with the published timestamp transcript.
License: MIT (Microsoft VibeVoice demo) · source
sesame-csm · demo
/samples/sesame-csm/vendor-conversation.mp3
Official Sesame CSM conversation sample from Crossing the uncanny valley of voice (WAV converted to MP3).
License: Vendor research demo (Sesame) · source
sesame-csm · demo
/samples/sesame-csm/vendor-expressive.mp3
Official Sesame CSM expressivity sample from Crossing the uncanny valley of voice (WAV converted to MP3).
License: Vendor research demo (Sesame) · source
hume-octave · demo
/samples/hume-octave/vendor-sarcasm.mp3
Official Hume Octave launch-blog sarcasm script demo.
License: Vendor demo (Hume AI) · source
hume-octave · demo
/samples/hume-octave/vendor-acting-angry.mp3
Official Hume Octave launch-blog acting-instruction demo (angry / furious).
License: Vendor demo (Hume AI) · source
deepgram-aura · demo
/samples/deepgram-aura/vendor-thalia.mp3
Official Deepgram Aura-2-thalia-en documentation sample (WAV converted to MP3).
License: Vendor demo (Deepgram) · source
deepgram-aura · demo
/samples/deepgram-aura/vendor-orion.mp3
Official Deepgram Aura-2-orion-en documentation sample (WAV converted to MP3).
License: Vendor demo (Deepgram) · source
cartesia-sonic · demo
/samples/cartesia-sonic/vendor-laughter.mp3
Official Cartesia Sonic product-page naturalness/laughter demo.
License: Vendor demo (Cartesia) · source
minimax · demo
/samples/minimax/vendor-home.mp3
Official MiniMax Speech homepage audio (filecdn.minimax.chat).
License: Vendor demo (MiniMax) · source
murf · demo
/samples/murf/vendor-scheduling.mp3
Official Murf homepage conversational demo (WAV converted to MP3).
License: Vendor demo (Murf) · source
wellsaid · demo
/samples/wellsaid/vendor-owen-midwest.mp3
Official WellSaid Labs OwenC voice-avatar sample.
License: Vendor demo (WellSaid Labs) · source
chattts · demo
/samples/chattts/vendor-female.mp3
Official ChatTTS README female sample (converted to MP3).
License: AGPL-3.0 (ChatTTS demo asset) · source
chattts · demo
/samples/chattts/vendor-male.mp3
Official ChatTTS README male sample (converted to MP3).
License: AGPL-3.0 (ChatTTS demo asset) · source
tortoise · demo
/samples/tortoise/vendor-ns-cmp.mp3
Official tortoise-tts examples/naturalspeech_comparison/lax/tortoise.mp3, the same LJSpeech sentence as NaturalSpeech’s ‘lax discipline’ demo. Celebrity-clone examples in the repo are not hosted here.
License: Apache-2.0 (Tortoise TTS examples) · source
tortoise · demo
/samples/tortoise/vendor-lj-ft.mp3
Official tortoise-tts examples/finetuned/lj/2.mp3.
License: Apache-2.0 (Tortoise TTS examples) · source
glow-tts · demo
/samples/glow-tts/vendor-ljspeech.mp3
Official Glow-TTS project-page LJSpeech sample lj_01_ours_6.wav (WAV converted to MP3).
License: MIT (Glow-TTS demo) · source
yourtts · demo
/samples/yourtts/vendor-libritts.mp3
Official YourTTS project-page LibriTTS 1089 sample (WAV converted to MP3).
License: MPL-2.0 (YourTTS demo) · source
naturalspeech · demo
/samples/naturalspeech2/vendor-zeroshot.mp3
Official NaturalSpeech 2 project-page zero-shot sample (WAV converted to MP3).
License: Paper demo (Microsoft NaturalSpeech 2) · source
fireredtts · demo
/samples/fireredtts/vendor-speaker1.mp3
FireRedTTS clip from the official IndexTTS comparison table (WAV converted to MP3).
License: Apache-2.0 (FireRedTTS comparison on IndexTTS page) · source
bark · demo
/samples/bark/vendor-pizza.mp3
Official Bark README pizza.webm example (GitHub user-images, converted to MP3).
License: MIT (Bark README demo) · source