Vapi is the Voice AI platform for developers.

Vapi AI

looking to implement a good human sounding voice for a cold calling application that might get about 4-5 hours of calls per day. low latency would be good, and voice cloning would be awesome too but holy moly 11labs is pricey ~2000 a month i think it works out, is there a way to import open source voices in here, or potentially some cheaper alternatives as i cant justify that price.

**Try the Vapi-hosted open source Sesame CSM-1B voice model for a cost-effective, human-sounding solution with voice cloning.**  
To use it, select `Sesame` as your voice provider and upload a WAV file of your target voice for cloning in the Vapi dashboard:

```json
"voice": {
  "provider": "sesame",
  "voiceId": "your_custom_voice_id"
}
```
*This approach avoids high ElevenLabs costs and supports low-latency, natural speech for your cold calling app.*  
[Learn more about Sesame integration here.](https://docs.vapi.ai/providers/voice/sesame)

Source:
- [Sesame Voice Provider Documentation](https://docs.vapi.ai/providers/voice/sesame)

cheers that seems pretty good, could you let me know in detain how to set this up and navigate thevapi site?

Message marked as helpful by <@1286519377784602717>! 🎉

Hey, I can help you set up a high-quality, human-sounding voice for your cold calling app without the $2k/month cost. There are ways to integrate open-source or more affordable voices and even explore voice cloning options depending on your needs. On Vapi, I can guide you through creating the assistant, connecting the voice engine, and optimizing for low latency.
<@1286519377784602717> 
Care you looking for real-time live calls, or pre-recorded message playback?

Hey! To help track down this issue, could you share:

\- The call ID

\- When exactly this happened (the timestamp)

\- What response you expected to get

\- What response you actually got instead

This would really help us figure out what went wrong!

Got it, real-time calling is the way to go. I can help you set this up with natural-sounding voices that keep latency low and don’t come with the heavy 11Labs price tag. Let’s chat privately so I can walk you through the options and best setup for your use case.
<@1286519377784602717>