scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-12 23:01:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 87

Merge pull request #20255 from BerriAI/litellm_tts_doc

Browse source 
Update Vertex AI Text to Speech doc to show use of audio
This commit is contained in:
Sameer Kankute 2026-02-02 16:16:28 +05:30 • committed by GitHub
commit 15cec5a4a0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
docs/my-website/docs/providers/vertex_speech.md
View file

@ -312,6 +312,7 @@ Gemini models with audio output capabilities using the chat completions API.
- Only supports `pcm16` audio format
- Streaming not yet supported
- Must set `modalities: ["audio"]`
- When using via LiteLLM Proxy, must include `"allowed_openai_params": ["audio", "modalities"]` in the request body to enable audio parameters
:::
### Quick Start
@ -372,7 +373,8 @@ curl http://0.0.0.0:4000/v1/chat/completions \
"model": "gemini-tts",
"messages": [{"role": "user", "content": "Say hello in a friendly voice"}],
"modalities": ["audio"],
"audio": {"voice": "Kore", "format": "pcm16"}
"audio": {"voice": "Kore", "format": "pcm16"},
"allowed_openai_params": ["audio", "modalities"]
}'
```
@ -389,6 +391,7 @@ response = client.chat.completions.create(
messages=[{"role": "user", "content": "Say hello in a friendly voice"}],
modalities=["audio"],
audio={"voice": "Kore", "format": "pcm16"},
extra_body={"allowed_openai_params": ["audio", "modalities"]}
)
print(response)
```