Transcribers

This page provides a comprehensive list of all supported vendors for Speech-to-Text (STT) services, along with their available configurations including languages, models, and voices.

​

Speech-to-Text (STT) Vendors

​

Microsoft

Value: microsoft Supported Languages:

---

​

Deepgram

Value: deepgram Supported Languages: Available Models:

---

​

Eleven Labs

Value: eleven-labs Supported Languages: Available Models:

---

​

Assembly AI

Value: assembly-ai Supported Languages:

---

​

Deepgram Self-Hosted

Value: deepgram-self-hosted Supported Languages: Available Models:

---

​

Usage Notes

• All vendor values should be used exactly as specified (case-sensitive)
• Language codes should match the format provided in the tables above
• Voice IDs and model values are vendor-specific and must be used exactly as shown
• Some vendors support additional configuration options (e.g., Cartesia supports emotion and speed settings)
• For streaming vendors, ensure your implementation supports streaming protocols

​

Get Support

Need help with vendor configuration? Reach out to us via developers@interactly.ai email. We’re here to help!