Developer documentation
Speech API reference
Giggy is a text-to-speech API for developers building voice agents and voice-enabled products. Generate speech through the native REST API, an OpenAI-compatible speech endpoint, a Vapi custom TTS endpoint, or Streamable HTTP MCP.
Core developer endpoints
- POST /v1/text-to-speech — native Giggy text-to-speech with Batch, Fast, and Streaming modes. Batch uses zero credits.
- POST /v1/audio/speech — OpenAI-compatible text-to-speech adapter for voice-product integrations.
- GET /v1/voices — list public Giggy voices.
- GET /v1/my-voices — list custom voices owned by the API-key scope.
- GET /v1/generations/{generationUuid} — read durable generation state and completed results.
- GET /v1/generations/{generationUuid}/stream — stream generation events and ordered PCM chunks using server-sent events.
- GET /v1/integrations/voices — public connector voice catalog.
- POST /v1/integrations/vapi/text-to-speech/{voiceId} — Vapi custom TTS webhook.
AI coding agents and MCP
Giggy exposes a Streamable HTTP MCP server at https://giggy.ai/mcp. MCP supports public voice discovery, owned custom-voice discovery, speech generation, and durable generation reads.
Voice-agent compatibility
The OpenAI-compatible speech endpoint can be used by compatible voice-agent frameworks. LiveKit can target the OpenAI-compatible endpoint. Pipecat integrations can use a custom TTSService adapter when UUID voice identifiers are not accepted by its built-in OpenAI service. These are compatibility paths, not native provider listings.
OpenAPI 3.1 specification · Speech API documentation · Pricing