Voices

​

List

from kupe import Kupe

client = Kupe()
voices = client.voices.list(provider="kupe")
for v in voices.items:
    print(v["id"], v.get("name"))

import { Kupe } from "kupe-sdk";

const kupe = new Kupe();
const voices = await kupe.voices.list({ provider: "kupe" });

curl "https://x.kupe.in/v1/voices?provider=kupe" \
  -H "Authorization: Bearer sk-kupe-YOUR_KEY"

curl https://x.kupe.in/v1/providers

​

Preview and speak

• GET /v1/voices/{voice_id}/preview — cached English+Hindi sample (audio body).
• POST /v1/voices/{voice_id}/speak — billed TTS for playground text. JSON { "text", "org_id", "language?", "speed?", "pitch?" }. Max 2000 characters. JWT required. Audio is not stored.

​

Clone, patch, delete

• POST /v1/voices/clone — multipart/form-data: name (unique after sanitize), sample (≤ 25 MB), optional is_public. Duplicate names return 409.
• PATCH /v1/voices/{voice_id} — rename or visibility. Rename must stay unique (409 if taken).
• GET /v1/voices/{voice_id}/usage — how many live agents still reference this clone
• DELETE /v1/voices/{voice_id} — optional fallback_voice_id for agents that still use it

# Dashboard / JWT session only
client.voices.clone(name="Priya desk", sample=open("clip.wav", "rb"))

await kupe.voices.clone({ name: "Priya desk", sample: file });

curl -X POST https://x.kupe.in/v1/voices/clone \
  -H "Authorization: Bearer $SUPABASE_JWT" \
  -F name="Priya desk" \
  -F sample=@clip.wav