AllModels

Verified

Unified TTS and STT API aggregating 18+ speech providers including Deepgram, ElevenLabs, OpenAI, AssemblyAI, Cartesia, Soniox, Groq, Fish Audio, MiniMax, Amazon Polly, Gemini, xAI Grok, and more. OpenAI and ElevenLabs SDK-compatible endpoints for text-to-speech synthesis, speech-to-text transcription, voice cloning, and voice discovery. Access 42+ TTS models and 39+ STT models through a single API key and unified interface.

skill.md (for agents) ↗

Endpoints

GET/el/v1/voices$0

List Voices (ElevenLabs SDK)

GET/el/v1/voices/search$0

Search Voices (ElevenLabs SDK)

POST/v1/custom-voices$0.01

Clone Voice

GET/v1/custom-voices$0

List Cloned Voices

GET/v1/custom-voices/{voice_id}$0

Get Cloned Voice

DELETE/v1/custom-voices/{voice_id}$0

Delete Cloned Voice

DELETE/el/v1/voices/{voice_id}$0

Delete Voice (ElevenLabs SDK)

POST/el/v1/voices/add$0.01

Clone Voice (ElevenLabs SDK)

GET/el/v1/voices/{voice_id}$0

Get Voice (ElevenLabs SDK)

GET/v1/voices$0

Search Voices

GET/v1/models$0

List Models

GET/v1/providers$0

List Providers

POST/el/v1/speech-to-textDynamic

Speech to Text (ElevenLabs SDK)

POST/oai/audio/speechDynamic

Text to Speech (OpenAI SDK)

POST/oai/audio/transcriptionsDynamic

Speech to Text (OpenAI SDK)

POST/el/v1/text-to-speech/{voice_id}Dynamic

Text to Speech Convert (ElevenLabs SDK)

POST/el/v1/text-to-speech/{voice_id}/streamDynamic

Text to Speech Stream (ElevenLabs SDK)

GET /el/v1/voices

const result = await orth.run({
  api: "allmodels",
  path: "/el/v1/voices",
});