Capabilities
Explore what Telephony supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Google Cloud
- Product
- Speech-to-Text
- Release Date
- Nov 6, 2023
- Data Policy
- Configurable
- Region
- US
- Input
- Audio
- Output
- Text
Playground
Try Telephony by Google Cloud. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Telephony.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Google Cloud | Not specified | Text | $0.0136 / minute | — | google/telephony:google |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | Not specified |
| Max seconds | 60 |
| Formats | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm |
Provider Notes
All three slugs support uploaded audio and live PCM through Google V2 StreamingRecognize. Chirp 3 adds automatic language selection, custom prompts, and stream endpointing sensitivity; its diarization is BatchRecognize-only and is therefore unavailable on AudioLab's synchronous upload and live paths. Chirp 2 adds speech translation and denoising but has a smaller documented streaming-language set and no diarization. Chirp 2 is routed to its supported us-central1 region by default, independently of the us multi-region used by Chirp 3 and Telephony. Telephony is tuned for phone audio (normally 8 kHz) and retains Google speaker diarization. Voice-activity timeouts must be greater than 500 ms and less than 60 seconds. AudioLab splits arbitrary audio frames at Google's 15 KiB RPC limit.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=google/telephony' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | google/telephony — Required model identifier. |
language_codes / max_alternatives | View Accepted Values |
profanity_filter / automatic_punctuation / spoken_punctuation / spoken_emojis | View Accepted Values |
multi_channel (upload) / diarization.min_speakers / diarization.max_speakers (Telephony) | View Accepted Values |
phrase_boost / transcript_normalization | View Accepted Values |
translation.target_language (Chirp 2) | View Accepted Values |
denoiser.denoise_audio / denoiser.snr_threshold (Chirp 2 and Chirp 3) | View Accepted Values |
custom_prompt / endpointing_sensitivity (Chirp 3) | View Accepted Values |
enable_voice_activity_events / voice_activity_timeout (streaming) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | Not specified |
| Max seconds | 60 |
| Formats | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Chirp 3Google Cloud | Not specified | $0.0136 / minute | — |
| Chirp 2Google Cloud | Not specified | $0.0136 / minute | — |
| MAI-Transcribe 2Microsoft Azure | Not specified | $0.0014 / minute | — |
| Gemini 3.5 TranscribeGoogle Gemini | Not specified | $0.0043 / minute | — |
| Saaras v4Sarvam AI | Not specified | ₹0.425 / minute | — |
| saaras-v4-batchSarvam AI | Not specified | ₹0.425 / minute | — |
