Kokoro voices — GGUF bundle

Per-speaker style packs for the Kokoro-82M family, converted to ggml's GGUF voice-pack format (arch=kokoro-voice, single F32 tensor voice.pack[max_phon, 1, 256]). For use with CrispStrobe/CrispASR alongside cstr/kokoro-82m-GGUF or the German backbone cstr/kokoro-de-hui-base-GGUF.

Each voicepack is ~510 KB. Loading is direct passthrough — no quantisation needed at this size.

Voices

The Tundragoon voicepacks are [512, 1, 256] F32 (max_phon=512); the official Kokoro and kikiri voicepacks are [510, 1, 256] F32 (max_phon=510). The voice loader reads max_phon from the file so both layouts work transparently.

German voice cascade

When CrispASR is invoked with -l de (or any de_* / de-* locale) and no explicit --voice, it picks German voicepacks in this order:

1. df_victoria — kikiri-tts, in-distribution to the dida-80b German backbone (recommended)
2. df_eva — Tundragoon recovery, second-tier German speaker
3. ff_siwis — French baseline, last-resort non-silence fallback

Languages without a native pack (ru, ko, ar, …) fall back to ff_siwis. See cstr/kokoro-de-hui-base-GGUF for the matching German backbone.

Quality (ASR roundtrip)

Long German phrase ("Guten Tag, dies ist ein Test des deutschen Phonemizers."), parakeet-tdt-0.6b-v3 -l de, dida-80b backbone F16:

All four clear the energy gate (peak ≥ 8000, RMS ≥ 1000); two are word-perfect on a phrase the official English-trained Kokoro-82M with af_heart collapses to silence on.

Quick start

huggingface-cli download cstr/kokoro-voices-GGUF kokoro-voice-af_heart.gguf --local-dir .
huggingface-cli download cstr/kokoro-82m-GGUF    kokoro-82m-q8_0.gguf       --local-dir .

./crispasr --backend kokoro \
    -m kokoro-82m-q8_0.gguf \
    --voice kokoro-voice-af_heart.gguf \
    --tts "Hello world" --tts-output hello.wav

Conversion

python models/convert-kokoro-voice-to-gguf.py \
    --input voices/af_heart.pt \
    --output kokoro-voice-af_heart.gguf

Attribution

• Official voices (af_heart, ef_dora, ff_siwis): hexgrad/Kokoro-82M, Apache-2.0.
• Tundragoon recovery (df_eva, dm_bernd): the original Tundragoon/Kokoro-German HF repo was deleted; voices were recovered from r1di/kokoro-fastapi-german's Git LFS (api/src/voices/v1_0/{df_eva,dm_bernd}.pt), retaining the original Apache-2.0 license.
• kikiri-tts (df_victoria, dm_martin): kikiri-tts/kikiri-german-victoria and kikiri-tts/kikiri-german-martin by the dida-80b maintainer, Apache-2.0.
• GGUF format + runtime: CrispStrobe/CrispASR.

Voice provenance (EU AI Act Art. 50(4))

Whose voice a pack reproduces is decided per pack, not by the backbone — a kokoro model is a base model, not a voice.

Synthesizing with df_eva or dm_bernd prepends a spoken AI disclosure: audio resembling an identifiable person is a deep fake under Art. 3(60) whether or not any cloning took place. It does not require --i-have-rights — the donor's agreement to the training is a licensing matter settled upstream, which a downstream operator cannot attest to.

Note the German cascade crosses this boundary. The documented fallback order is df_victoria → df_eva → ff_siwis, so a missing default silently moves you from a synthetic voice to a real HUI narrator. That is exactly why the disclosure follows the pack rather than the run.

Override per run with --speaker-identity, or stamp a pack permanently with models/stamp-speaker-identity.py. See docs/eu-ai-act.md §6.2a.

License

Apache-2.0 across the bundle, matching every upstream source.