Recording... press "Stop recording" to stop
Note: You need an LLM a audio-transcription(whisper) and a tts model installed in order for this to work. Select the appropariate model from the toolbox and then click the 'Talk' button to start recording. The recording will continue until you click 'Stop recording'. Make sure your microphone is set up and enabled.
LLM Model:
Select a model
phi-3-vision:vllm
voice-no-talesyntese-medium
whisper-large-q5_0
LocalAI-functioncall-phi-4-v0.3
bunny-llama-3-8b-v
arcee-spark
tts-1
lb-reranker-0.5b-v1.0
sd-3.5-medium-ggml
gpt-4
whisper-1
llama3.2-3b-enigma
tts-1-hd
loki-v2.6-8b-1024k
wizardlm2-7b
bark-cpp
dreamshaper
gpt-4o
samsungsailmontreal_bytecraft
meta-llama-3.1-8b-instruct:grammar-functioncall
qwen3-0.6b
qwen3-1.7b
snowflake-arctic-embed-m-v2.0
voice-en-us-libritts-high
voice-en-us-ryan-high
stablediffusion
homercreativeanvita-mix-qw7b
cross-encoder
jina-reranker-v1-base-en
llama3.2-3b-esper2
moondream2
silero-vad
text-embedding-ada-002
snowflake-arctic-embed-l-v2.0
whisper-norwegian-small
Bunny-Llama-3-8B-Q4_K_M-mmproj.gguf
Promt-generator.i1-Q5_K_M.gguf
b5869d55688a529c3738cb044e92c331
clip_g-Q4_0.gguf
clip_l-Q4_0.gguf
ggml-model-whisper-large-q5_0.bin
llava-v1.6-7b-mmproj-f16.gguf
micro
model_int8.onnx
moondream2-mmproj-f16.gguf
t5xxl-Q4_0.gguf
Whisper Model:
Select a model
phi-3-vision:vllm
voice-no-talesyntese-medium
whisper-large-q5_0
LocalAI-functioncall-phi-4-v0.3
bunny-llama-3-8b-v
arcee-spark
tts-1
lb-reranker-0.5b-v1.0
sd-3.5-medium-ggml
gpt-4
whisper-1
llama3.2-3b-enigma
tts-1-hd
loki-v2.6-8b-1024k
wizardlm2-7b
bark-cpp
dreamshaper
gpt-4o
samsungsailmontreal_bytecraft
meta-llama-3.1-8b-instruct:grammar-functioncall
qwen3-0.6b
qwen3-1.7b
snowflake-arctic-embed-m-v2.0
voice-en-us-libritts-high
voice-en-us-ryan-high
stablediffusion
homercreativeanvita-mix-qw7b
cross-encoder
jina-reranker-v1-base-en
llama3.2-3b-esper2
moondream2
silero-vad
text-embedding-ada-002
snowflake-arctic-embed-l-v2.0
whisper-norwegian-small
Bunny-Llama-3-8B-Q4_K_M-mmproj.gguf
Promt-generator.i1-Q5_K_M.gguf
b5869d55688a529c3738cb044e92c331
clip_g-Q4_0.gguf
clip_l-Q4_0.gguf
ggml-model-whisper-large-q5_0.bin
llava-v1.6-7b-mmproj-f16.gguf
micro
model_int8.onnx
moondream2-mmproj-f16.gguf
t5xxl-Q4_0.gguf
TTS Model:
Select a model
phi-3-vision:vllm
voice-no-talesyntese-medium
whisper-large-q5_0
LocalAI-functioncall-phi-4-v0.3
bunny-llama-3-8b-v
arcee-spark
tts-1
lb-reranker-0.5b-v1.0
sd-3.5-medium-ggml
gpt-4
whisper-1
llama3.2-3b-enigma
tts-1-hd
loki-v2.6-8b-1024k
wizardlm2-7b
bark-cpp
dreamshaper
gpt-4o
samsungsailmontreal_bytecraft
meta-llama-3.1-8b-instruct:grammar-functioncall
qwen3-0.6b
qwen3-1.7b
snowflake-arctic-embed-m-v2.0
voice-en-us-libritts-high
voice-en-us-ryan-high
stablediffusion
homercreativeanvita-mix-qw7b
cross-encoder
jina-reranker-v1-base-en
llama3.2-3b-esper2
moondream2
silero-vad
text-embedding-ada-002
snowflake-arctic-embed-l-v2.0
whisper-norwegian-small
Bunny-Llama-3-8B-Q4_K_M-mmproj.gguf
Promt-generator.i1-Q5_K_M.gguf
b5869d55688a529c3738cb044e92c331
clip_g-Q4_0.gguf
clip_l-Q4_0.gguf
ggml-model-whisper-large-q5_0.bin
llava-v1.6-7b-mmproj-f16.gguf
micro
model_int8.onnx
moondream2-mmproj-f16.gguf
t5xxl-Q4_0.gguf
Talk
Reset conversation