AudioDojo
One chute, 12 models, 13 endpoints — covering text-to-speech, voice cloning, voice design, transcription, denoising, source separation, speaker verification, VAD, and language detection. Including Kokoro-82M, Qwen3-TTS 1.7B, Whisper large-v3-turbo, NVIDIA Canary-Qwen 2.5B, and NVIDIA Parakeet TDT.
AudioDojo bundles speech generation, voice cloning, transcription, speaker analysis, denoising, and separation. Pick a task and the input form adapts to it.
Ultra-fast text-to-speech with built-in multilingual Kokoro voices.
Sign in to use the playground
Run this model with your Chutes account, quota, and API access.
Model facts & API quick start
AudioDojo is served on Chutes inside a Trusted Execution Environment (TEE). Call it at https://vonkaiser-audiodojo.chutes.ai/tts/kokoro with a Chutes API key.
AudioDojo at a glance
- Model ID
AudioDojo- Deployed by
- vonkaiser
- Type
- Speech
- Compute price
- $2.25 per hour
- Modalities
- text, audio in → audio, text out
- Confidential compute (TEE)
- Yes, runs in a Trusted Execution Environment
- Architecture
- Multi-model audio toolkit: 12 models behind 14 REST paths on one chute, all resident in GPU memory
- License
- Mixed per model: Apache-2.0 (Kokoro, Qwen3-TTS, SpeechBrain), MIT (Whisper large-v3-turbo, Silero VAD), CC-BY-4.0 (NVIDIA Canary, Parakeet)
- TTS
- Kokoro-82M (54 voices), Qwen3-TTS 1.7B (clone, custom speakers, voice design)
- STT
- Whisper large-v3-turbo (multilingual), Canary-Qwen 2.5B (English), Parakeet TDT 0.6B v3 (25 European languages)
- Audio processing
- Silero VAD, MetricGAN+ denoise, SepFormer separation, ECAPA-TDNN speaker verification, Whisper language detection, diarization
- Cold starts
- None between endpoints; every model stays loaded in GPU memory (per chute readme)
API quick start
- Base URL
https://vonkaiser-audiodojo.chutes.ai- Endpoint
POST /tts/kokoro- Auth header
Authorization: Bearer $CHUTES_API_KEY
curl -X POST "https://vonkaiser-audiodojo.chutes.ai/tts/kokoro" \
-H "Authorization: Bearer $CHUTES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Your text here",
"speed": 1,
"voice": "af_heart"
}' \
--output output.wavAudioDojo FAQ
Which model serves which endpoint?
TTS: /speak and /tts/kokoro use Kokoro-82M; /tts/qwen3clone, /tts/qwen3custom, and /tts/qwen3design use Qwen3-TTS 1.7B (Base, CustomVoice, and VoiceDesign checkpoints respectively). STT: /stt/whisper is Whisper large-v3-turbo, /stt/canary is NVIDIA Canary-Qwen 2.5B, /stt/parakeet is NVIDIA Parakeet TDT 0.6B v3. Processing: /audio/vad is Silero VAD, /audio/denoise is MetricGAN+, /audio/separate is SepFormer, /audio/verifyspeaker is ECAPA-TDNN, /audio/detectlanguage is Whisper, and /audio/diarize is a diarization pipeline (model unnamed in the chute readme).
How does voice cloning work and what reference audio do I need?
POST to /tts/qwen3clone with ref_audio_b64 (a base64 reference clip of up to 6 seconds), the text to speak, and optionally ref_text (its transcript; Whisper auto-transcribes if omitted). Set trim_sample true to auto-trim longer clips, auto_denoise true to clean noisy references with MetricGAN+, and high_fidelity true for ICL mode, which mimics prosody more closely but can bleed the reference's last syllable into the output.
Which STT endpoint should I pick?
Whisper large-v3-turbo for multilingual audio (99 languages) with optional word timestamps. Canary-Qwen 2.5B for the highest-accuracy English transcription, especially complex or domain-specific audio; it is English-only. Parakeet TDT 0.6B v3 for fast transcription of 25 European languages with word and segment timestamps and automatic punctuation.
What formats do requests and responses use?
All requests are flat JSON. Audio inputs are base64 strings in fields like audio_b64 and ref_audio_b64, accepting common audio formats. TTS endpoints (/speak, /tts/*) and the denoise/separate endpoints return raw audio/wav bytes; STT, VAD, diarization, speaker verification, and language detection return JSON.
Is /speak compatible with the old standalone Kokoro chute?
Yes, by design. It keeps the same request and response contract (text, voice, speed in, audio/wav at 24 kHz out) and runs the identical Kokoro-82M pipeline as /tts/kokoro. Migrating from chutes-kokoro means changing only the base URL to https://vonkaiser-audiodojo.chutes.ai.
Can I use the outputs commercially?
Licenses vary per bundled model: Kokoro, Qwen3-TTS, MetricGAN+, and ECAPA-TDNN are Apache-2.0; Whisper large-v3-turbo is MIT; NVIDIA's Canary-Qwen and Parakeet are CC-BY-4.0 (commercial use permitted with attribution, per their model cards). Check the license of the specific model behind the endpoint you use.
Do models cold-start when I switch endpoints?
No. The chute readme states all 12 models are loaded in GPU memory at all times, so any endpoint responds without a model-load delay. This is the main operational advantage over running 12 separate single-model deployments.
What languages does Qwen3-TTS support?
Ten, per the Qwen3-TTS model cards: Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian, plus several dialect voice profiles. Pass the target language name in the endpoint's language field (default English).