Soniqosoniqo
Documentation

Changelog

Recent changes to the Soniqo Cloud API — new endpoints, capabilities, and compatibility.

2026-06-23

Speech synthesis, voice cloning & voice agents

  • Text-to-speech — generate natural speech via /v1/audio/speech (OpenAI-compatible) and /v1/synthesize.
  • Voice cloning — register a voice from a short clip with /v1/voices and reuse it on any synthesis call. Included — no per-voice fee.
  • Low-latency streaming — 24 kHz PCM from response_format=pcm, and Authorization: Bearer now accepts an API key, so the OpenAI / ElevenLabs SDKs and agent frameworks like LiveKit work with a base-URL change. See the voice-agents guide.
  • Console — synthesize and manage cloned voices from the browser.
2026-06-23

Simpler, competitive pricing

  • Transcription $0.24 / audio-hour, synthesis $0.22 / minute (cloning included), billed per second.
  • Free tier is now $10 / month of credit — no card needed to start.
2026-06

Transcription

  • Speaker diarization and identification bundled into every transcription.
  • Expanded language and dialect coverage; auto-detect or hint the language.
  • OpenAI-Whisper-compatible (/v1/audio/transcriptions), async for long audio (/v1/transcribe), and realtime streaming (/v1/realtime).