> For the complete documentation index, see [llms.txt](https://docs.qolaba.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qolaba.ai/speech-generation/speech-generation-modes.md).

# Speech Generation Modes

Qolaba's Speech Generation supports two modes — **Single Speaker** and **Multi-Speaker**. The mode you choose determines how your script is structured, how many voices are involved, and what kind of audio output is produced.

***

#### Single Speaker vs. Multi-Speaker

|                   | Single Speaker Mode                       | Multi-Speaker Mode                                    |
| ----------------- | ----------------------------------------- | ----------------------------------------------------- |
| **Voices**        | One voice throughout                      | Two distinct voices alternating                       |
| **Script format** | Continuous text input                     | Structured dialogue cards per speaker                 |
| **Output**        | Single narration audio file               | Single combined audio file with alternating voices    |
| **Best for**      | Narration, voiceovers, announcements, ads | Podcasts, interviews, dialogues, training simulations |
| **Configuration** | Voice, accent, style, script              | Voice per speaker, accent, style, dialogue sequence   |

***

#### When to Use Single Speaker Mode

Single Speaker Mode is the right choice when one voice delivers the entire content — narrating, announcing, or presenting without interruption or dialogue.

Use it for:

* Voiceovers for videos, ads, and presentations
* Podcast introductions and solo episode narration
* Product walkthrough and demo scripts
* Instructional and training audio
* Announcements and public communications
* Audiobook-style storytelling

***

#### When to Use Multi-Speaker Mode

Multi-Speaker Mode is the right choice when the content involves a conversation, exchange, or dialogue between two distinct voices.

Use it for:

* Podcast interviews and co-hosted episodes
* Q\&A and FAQ format audio
* Story-based scripts with two characters
* Training simulations and role-play scenarios
* Conversational product demos
* Interview-style marketing content

***

#### What's in This Section

1. [**Single Speaker Mode →**](/speech-generation/speech-generation-modes/single-speaker-mode.md) How to configure and generate single-voice narration — covering voice selection, accent, style instructions, script input, model selection, and output.
2. [**Multi-Speaker Mode →**](/speech-generation/speech-generation-modes/multi-speaker-mode.md) How to configure and generate two-voice dialogue audio — covering voice assignment per speaker, the dialogue card system, accent and style, and generating a combined audio output.