Skip to content

Update stt tts docs for multiprovider #621

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mahajantejas wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Update stt tts docs for multiprovider #621

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a239a27
Revise ElevenLabs section and add alternative provider note
mahajantejas May 21, 2026
68dfe7f
Add Eleven Labs integration details to documentation
mahajantejas May 21, 2026
26f19ee
Include information on alternative TTS providers
mahajantejas May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 1 addition & 30 deletions docs/5. Integrations/Speech to text capabilities in Glific.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,33 +63,4 @@ By specifying the `output_language` parameter, this configuration ensures that a


## Using other providers
Apart from Gemini which is the default speech engine used by Glific, Eleven Labs can be used as a provider. This can be configured as the provider to use for transcription purposes by explicitly providing additional parameters of `provider` and `model`.

### Eleven Labs

To reference the eleven labs provider, pass the following additional parameters in the webhook body
```
"provider":"elevenlabs",
"model":"scribe_v2"

```
<img width="678" height="484" alt="Screenshot 2026-05-08 at 4 26 45 PM" src="https://github.com/user-attachments/assets/9f35331c-7f39-44ad-9471-8042281acfa8" />

**Eleven labs integration does not support translation to any specified output language.**

## Main differences between Gemini and Eleven Labs:
#### Translation Support

- Gemini: Full translation support - can transcribe audio in one language and translate to another (e.g., Hindi audio → English text)
- ElevenLabs: No translation - only transcribes audio in its original language. Good for transcription-only use cases

#### Language Support & Flexibility

- Gemini: Supports auto-language detection AND explicit language specification. More flexible for mixed-language or unknown audio
- ElevenLabs: Limited to 13 specific languages (mostly Indic languages + English). Requires knowing or auto-detecting the language beforehand

## Decision Guide:

- Choose ElevenLabs if: You only need simple, fast transcription of supported languages (mainly Indic languages) and want a lightweight solution
- Else continue to stick with the default model of gemini provided by Glific

It is possible to use ElevenLabs, Sarvam and other providers, through this webhook instead of Google Gemini, if the organization has acquired credits from any of these providers. Reach out to the Glific team at support@glific.org to know more.
30 changes: 3 additions & 27 deletions docs/5. Integrations/Text to speech capabilities in Glific.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,34 +96,8 @@ Please note: **`provider` and `model` must always be specified together.** If yo

Here, the `model` or `voice` parameters can be mixed and matched from the values mentioned in the table above.

## Using Elevenlabs model and voices as alternative to google gemini
- **Provider Name**: `elevenlabs`
### ElevenLabs TTS Models
| Model Name | Description |
|---|---|
| `eleven_v3` | Latest ElevenLabs TTS model |

### ElevenLabs Voices
| Voice Name | Characteristics | Gender | Best For |
|---|---|---|---|
| **Sarah** | Clear, professional, warm | Female | Professional, educational content |
| **George** | Deep, authoritative, formal | Male | Formal documents, corporate content |
| **Callum** | Bright, friendly, youthful | Male | Casual, conversational content |
| **Liam** | Neutral, clear, balanced | Male | General purpose content |

```
"provider" : "elevenlabs",
"model" : "eleven_v3",
"voice" : "Liam"
```
Above are the additional parameters that can be passed via the function body to explicitly call elevenlabs' model and voices.

<img width="620" height="441" alt="Screenshot 2026-04-27 at 12 10 26 PM" src="https://github.com/user-attachments/assets/1987831c-28a0-44f5-ab22-aa243bed0d2d" />

Please note: **`provider` and `model` must always be specified together.** If you set one, you must set the other — specifying only a provider or only a model will cause a webhook error.


#### Google (Gemini) & ElevenLabs Supported Languages
#### Supported Languages

- English
- Hindi
Expand All @@ -138,3 +112,5 @@ Please note: **`provider` and `model` must always be specified together.** If yo
- Odia (works best with elevenlabs)
- Sindhi

## Using other providers
It is possible to use ElevenLabs, Sarvam and other providers, through this webhook instead of Google Gemini, if the organization has acquired credits from any of these providers. Reach out to the Glific team at support@glific.org to know more.
Loading