Bilingual voice system for a customer-operations team
Problem shape
Calls needed to be handled conversationally in two languages, without building and maintaining a separate call flow for each. For a voice agent to feel usable, the pause between a caller finishing and hearing a reply has to be short — so speed was a design constraint, not a nice-to-have.
What was built
- A voice pipeline combining telephony, streaming speech-to-text, a language model and synthesised speech
- Conversation handling in either of two languages
- Latency work across each stage of a conversational turn
How it fits the workflow
The system sits on the phone line in front of the team. Each turn was broken into stages — end-of-speech detection, transcription, reasoning, speech synthesis and playback — so each could be measured and improved separately rather than guessed at as a whole.
- Services:
- Voice AI & telephony
- Built with:
- Twilio · Deepgram · OpenAI · ElevenLabs