speech-to-text

Name: speech-to-text
Author: inference-sh

564installs94forks

How to install speech-to-text?

inference-sh/skills/speech-to-text

$npx -y skills add inference-sh/skills --skill speech-to-text

Installs into the current project.

Summary

Transcribe audio to text with ElevenLabs Scribe and Whisper models via inference.sh CLI. Models: ElevenLabs Scribe v2 (98%+ accuracy, diarization), Fast Whisper Large V3, Whisper V3 Large. Capabilities: transcription, translation, multi-language, timestamps, speaker diarization,

Files · 1

View on GitHub

SKILL.md

1	> Install the belt CLI skill: `npx skills add belt-sh/cli`
2
3	# Speech-to-Text
4
5	Transcribe audio to text via [inference.sh](https://inference.sh) CLI.
6
7	![Speech-to-Text](https://cloud.inference.sh/u/4mg21r6ta37mpaz6ktzwtt8krr/01jz025e88nkvw55at1rqtj5t8.png)
8
9	## Quick Start
10
11	> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
12
13	```bash
14	belt login
15
16	belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "https://audio.mp3"}'
17	```
18
19
20	## Available Models
21
22	\| Model \| App ID \| Best For \|
23	\|-------\|--------\|----------\|
24	\| ElevenLabs Scribe v2 \| `elevenlabs/stt` \| 98%+ accuracy, diarization, 90+ languages \|
25	\| Fast Whisper V3 \| `infsh/fast-whisper-large-v3` \| Fast transcription \|
26	\| Whisper V3 Large \| `infsh/whisper-v3-large` \| Highest accuracy \|
27
28	## Examples
29
30	### Basic Transcription
31
32	```bash
33	belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "https://meeting.mp3"}'
34	```
35
36	### With Timestamps
37
38	```bash
39	belt app sample infsh/fast-whisper-large-v3 --save input.json
40
41	# {
42	# "audio_url": "https://podcast.mp3",
43	# "timestamps": true
44	# }
45
46	belt app run infsh/fast-whisper-large-v3 --input input.json
47	```
48
49	### Translation (to English)
50
51	```bash
52	belt app run infsh/whisper-v3-large --input '{
53	"audio_url": "https://french-audio.mp3",
54	"task": "translate"
55	}'
56	```
57
58	### From Video
59
60	```bash
61	# Extract audio from video first
62	belt app run infsh/video-audio-extractor --input '{"video_url": "https://video.mp4"}' > audio.json
63
64	# Transcribe the extracted audio
65	belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "<audio-url>"}'
66	```
67
68	## Workflow: Video Subtitles
69
70	```bash
71	# 1. Transcribe video audio
72	belt app run infsh/fast-whisper-large-v3 --input '{
73	"audio_url": "https://video.mp4",
74	"timestamps": true
75	}' > transcript.json
76
77	# 2. Use transcript for captions
78	belt app run infsh/caption-videos --input '{
79	"video_url": "https://video.mp4",
80	"captions": "<transcript-from-step-1>"
81	}'
82	```
83
84	## Supported Languages
85
86	Whisper supports 99+ languages including:
87	English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and many more.
88
89	## Use Cases
90
91	- Meetings: Transcribe recordings
92	- Podcasts: Generate transcripts
93	- Subtitles: Create captions for videos
94	- Voice Notes: Convert to searchable text
95	- Interviews: Transcription for research
96	- Accessibility: Make audio content accessible
97
98	## Output Format
99
100	Returns JSON with:
101	- `text`: Full transcription
102	- `segments`: Timestamped segments (if requested)
103	- `language`: Detected language
104
105	## Related Skills
106
107	```bash
108	# ElevenLabs STT (98%+ accuracy, diarization)
109	npx skills add inference-sh/skills@elevenlabs-stt
110
111	# ElevenLabs TTS (reverse direction)
112	npx skills add inference-sh/skills@elevenlabs-tts
113
114	# Full platform skill (all apps)
115	npx skills add inference-sh/skills@infsh-cli
116
117	# Text-to-speech (reverse direction)
118	npx skills add inference-sh/skills@text-to-speech
119
120	# Video generation (add captions)
121	npx skills add inference-sh/skills@ai-video-generation
122
123	# AI avatars (lipsync with transcripts)
124	npx skills add inference-sh/skills@ai-avatar-video
125	```
126
127	Browse all audio apps: `belt app store --category audio`
128
129	## Documentation
130
131	- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
132	- [Audio Transcription Example](https://inference.sh/docs/examples/audio-transcription) - Complete transcription guide
133	- [Apps Overview](https://inference.sh/docs/apps/overview) - Understanding the app ecosystem

People who liked this also viewed

6 picks

Type

speech-to-text

564installs94forks

View on GitHub

How to install speech-to-text?

inference-sh/skills/speech-to-text

$npx -y skills add inference-sh/skills --skill speech-to-text

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	> Install the belt CLI skill: `npx skills add belt-sh/cli`
2
3	# Speech-to-Text
4
5	Transcribe audio to text via [inference.sh](https://inference.sh) CLI.
6
7	![Speech-to-Text](https://cloud.inference.sh/u/4mg21r6ta37mpaz6ktzwtt8krr/01jz025e88nkvw55at1rqtj5t8.png)
8
9	## Quick Start
10
11	> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
12
13	```bash
14	belt login
15
16	belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "https://audio.mp3"}'
17	```
18
19
20	## Available Models
21
22	\| Model \| App ID \| Best For \|
23	\|-------\|--------\|----------\|
24	\| ElevenLabs Scribe v2 \| `elevenlabs/stt` \| 98%+ accuracy, diarization, 90+ languages \|
25	\| Fast Whisper V3 \| `infsh/fast-whisper-large-v3` \| Fast transcription \|
26	\| Whisper V3 Large \| `infsh/whisper-v3-large` \| Highest accuracy \|
27
28	## Examples
29
30	### Basic Transcription
31
32	```bash
33	belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "https://meeting.mp3"}'
34	```
35
36	### With Timestamps
37
38	```bash
39	belt app sample infsh/fast-whisper-large-v3 --save input.json
40
41	# {
42	# "audio_url": "https://podcast.mp3",
43	# "timestamps": true
44	# }
45
46	belt app run infsh/fast-whisper-large-v3 --input input.json
47	```
48
49	### Translation (to English)
50
51	```bash
52	belt app run infsh/whisper-v3-large --input '{
53	"audio_url": "https://french-audio.mp3",
54	"task": "translate"
55	}'
56	```
57
58	### From Video
59
60	```bash
61	# Extract audio from video first
62	belt app run infsh/video-audio-extractor --input '{"video_url": "https://video.mp4"}' > audio.json
63
64	# Transcribe the extracted audio
65	belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "<audio-url>"}'
66	```
67
68	## Workflow: Video Subtitles
69
70	```bash
71	# 1. Transcribe video audio
72	belt app run infsh/fast-whisper-large-v3 --input '{
73	"audio_url": "https://video.mp4",
74	"timestamps": true
75	}' > transcript.json
76
77	# 2. Use transcript for captions
78	belt app run infsh/caption-videos --input '{
79	"video_url": "https://video.mp4",
80	"captions": "<transcript-from-step-1>"
81	}'
82	```
83
84	## Supported Languages
85
86	Whisper supports 99+ languages including:
87	English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and many more.
88
89	## Use Cases
90
91	- Meetings: Transcribe recordings
92	- Podcasts: Generate transcripts
93	- Subtitles: Create captions for videos
94	- Voice Notes: Convert to searchable text
95	- Interviews: Transcription for research
96	- Accessibility: Make audio content accessible
97
98	## Output Format
99
100	Returns JSON with:
101	- `text`: Full transcription
102	- `segments`: Timestamped segments (if requested)
103	- `language`: Detected language
104
105	## Related Skills
106
107	```bash
108	# ElevenLabs STT (98%+ accuracy, diarization)
109	npx skills add inference-sh/skills@elevenlabs-stt
110
111	# ElevenLabs TTS (reverse direction)
112	npx skills add inference-sh/skills@elevenlabs-tts
113
114	# Full platform skill (all apps)
115	npx skills add inference-sh/skills@infsh-cli
116
117	# Text-to-speech (reverse direction)
118	npx skills add inference-sh/skills@text-to-speech
119
120	# Video generation (add captions)
121	npx skills add inference-sh/skills@ai-video-generation
122
123	# AI avatars (lipsync with transcripts)
124	npx skills add inference-sh/skills@ai-avatar-video
125	```
126
127	Browse all audio apps: `belt app store --category audio`
128
129	## Documentation
130
131	- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
132	- [Audio Transcription Example](https://inference.sh/docs/examples/audio-transcription) - Complete transcription guide
133	- [Apps Overview](https://inference.sh/docs/apps/overview) - Understanding the app ecosystem

People who liked this also viewed

6 picks

Type