Audio

Text to speech

curl "$CCSIO_BASE_URL/audio/speech" \
  -H "Authorization: Bearer $CCSIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "kokoro-82m", "input": "Welcome to the AI Control Plane.", "voice": "af_heart", "response_format": "wav"}' \
  --output welcome.wav

input: up to 4,096 characters.
response_format: wav (24 kHz, mono, 16-bit) or pcm.
speed: from 0.25 to 4.
voice: one of the voices below; af_heart when you send none.

Language	Voices
English (US)	`af_heart`, `af_bella`, `af_nova`, `am_adam`, `am_michael` and more
English (UK)	`bf_emma`, `bf_isabella`, `bm_george`, `bm_lewis` and more
Spanish	`ef_dora`, `em_alex`, `em_santa`
French	`ff_siwis`
Italian	`if_sara`, `im_nicola`
Portuguese (Brazil)	`pf_dora`, `pm_alex`, `pm_santa`
Hindi	`hf_alpha`, `hf_beta`, `hm_omega`, `hm_psi`

Speech to text

curl "$CCSIO_BASE_URL/audio/transcriptions" \
  -H "Authorization: Bearer $CCSIO_API_KEY" \
  -F model=whisper-large-v3 \
  -F [email protected]

JSON

{ "text": "Welcome to the AI Control Plane." }

Send the audio as multipart/form-data; the whole upload may be up to 25 MiB.
language (for example es or de) helps when you know the language.
response_format: json (default), text, srt, vtt or verbose_json with segments and timestamps.

Text to speech

Speech to text

Get your first API key