> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rime.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Build real-time voice experiences

> Generate natural speech, transcribe audio, build responsive voice agents, and run Rime in production.

# Build real-time voice experiences

Generate natural speech, build responsive voice agents, and run Rime in production.

[Generate your first audio](https://docs.rime.ai/docs/quickstart-five-minute.md)

[Build a voice agent](https://docs.rime.ai/docs/voice-agents.md)

[Explore voices & models](https://docs.rime.ai/docs/voices.md)

Need a key? Create an API token in the [Rime dashboard](https://app.rime.ai/tokens).

First request

## Go from text to audio

Set `RIME_API_KEY`, run one of these examples, and play the generated `hello.mp3` file. If you hear "Hello from Rime," your key and request both work.

```bash cURL theme={null}
curl --request POST \
  --url https://coda.api.rime.ai/ \
  --header "Authorization: Bearer $RIME_API_KEY" \
  --header "Content-Type: application/json" \
  --header "Accept: audio/mpeg" \
  --fail \
  --show-error \
  --output hello.mp3 \
  --data '{
    "speaker": "astra",
    "text": "Hello from Rime.",
    "lang": "en"
  }'
```

```python Python theme={null}
import os
import requests

response = requests.post(
    "https://coda.api.rime.ai/",
    headers={
        "Authorization": f"Bearer {os.environ['RIME_API_KEY']}",
        "Accept": "audio/mpeg",
    },
    json={
        "speaker": "astra",
        "text": "Hello from Rime.",
        "lang": "en",
    },
)
response.raise_for_status()

with open("hello.mp3", "wb") as audio:
    audio.write(response.content)
```

```javascript JavaScript theme={null}
// Save as hello.mjs so Node runs it as an ES module.
import { writeFile } from "node:fs/promises";

const response = await fetch("https://coda.api.rime.ai/", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.RIME_API_KEY}`,
    "Content-Type": "application/json",
    Accept: "audio/mpeg",
  },
  body: JSON.stringify({
    speaker: "astra",
    text: "Hello from Rime.",
    lang: "en",
  }),
});

if (!response.ok) throw new Error(`Rime API error: ${response.status}`);
await writeFile("hello.mp3", Buffer.from(await response.arrayBuffer()));
```

[TTS in five minutes](https://docs.rime.ai/docs/quickstart-five-minute.md) is the complete walkthrough. The [Rime CLI](https://docs.rime.ai/docs/quickstart-cli.md) covers the same steps from the terminal.

Choose what you're building

## Start with the path that matches your application

Text-to-speech runs over HTTP and WebSockets, speech-to-text over WebSockets and gRPC, and Prism over a WebSocket.

> [card] [Add speech to an application](https://docs.rime.ai/docs/quickstart-five-minute.md)
>
> Generate speech over HTTP, stream the response, and play it in your application.

> [card] [Transcribe speech](https://docs.rime.ai/docs/speech-to-text.md)
>
> Stream English or Spanish audio from your backend, show partial transcripts while the person speaks, and act on the final one.

> [card] [Run a speech-to-speech agent](https://docs.rime.ai/docs/prism/overview.md)
>
> Send a caller's audio to Prism, which takes turns, handles interruptions, and replies in speech with your instructions and tools.

> [card] [Build a real-time voice agent](https://docs.rime.ai/docs/voice-agents.md)
>
> Pair Rime text-to-speech, and optionally Rime speech-to-text, with your LLM and audio transport for responsive conversations.

> [card] [Deploy on your infrastructure](https://docs.rime.ai/docs/on-prem/quickstart.md)
>
> Run Rime privately with Docker Compose or Kubernetes.

Developer journey

## From first audio to production

Follow the lifecycle or jump directly to the problem you're solving.

### Get started

[Generate your first audio](https://docs.rime.ai/docs/quickstart-five-minute.md)
[Transcribe your first recording](https://docs.rime.ai/docs/stt/quickstart.md)
[Talk to your first Prism agent](https://docs.rime.ai/docs/prism/quickstart.md)
[Create an API token](https://app.rime.ai/tokens)
[Authenticate requests](https://docs.rime.ai/docs/api-authentication.md)
[Choose a voice](https://docs.rime.ai/docs/voices.md)

### Build

[Stream audio over HTTP](https://docs.rime.ai/docs/streaming.md)
[Use WebSockets](https://docs.rime.ai/docs/websockets.md)
[Build with LiveKit](https://docs.rime.ai/docs/quickstart-livekit.md)
[Integrate with Pipecat](https://docs.rime.ai/docs/pipecat.md)

### Customize

[Choose a model](https://docs.rime.ai/docs/models.md)
[Guide delivery with prompts](https://docs.rime.ai/docs/prompting.md)
[Control pronunciation](https://docs.rime.ai/platform/pronunciation-control.md)
[Format text](https://docs.rime.ai/docs/text-normalization.md)

### Operate

[Reduce latency](https://docs.rime.ai/docs/latency.md)
[Deploy on-prem](https://docs.rime.ai/docs/on-prem/quickstart.md)
[Review privacy and compliance](https://docs.rime.ai/docs/privacy-compliance.md)

Models and voices

## Choose a model and voice

Voice availability depends on the model and language, so compare models first.

> [card] [Compare models](https://docs.rime.ai/docs/models.md)
>
> Understand the tradeoffs across Coda and Mist before choosing a model ID.

> [card] [Browse voices](https://docs.rime.ai/docs/voices.md)
>
> Explore the voice catalog and find voices available for your model and language.

Resources

## Reference and tooling

> [card] [API reference](https://docs.rime.ai/docs/api-reference.md)
>
> Endpoints, parameters, formats, and examples.

> [card] [API cheat sheet](https://docs.rime.ai/docs/api-cheat-sheet.md)
>
> Common requests and endpoints on one page.

> [card] [CLI](https://docs.rime.ai/docs/quickstart-cli.md)
>
> Generate and inspect audio from your terminal.

> [card] [MCP server](https://docs.rime.ai/docs/mcp.md)
>
> Use Rime from Claude, Codex, and compatible IDEs.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.